Last Received
theepochtimes Thu, 13 Aug 2026 17:20
theoriginalunderground Thu, 13 Aug 2026 16:26
fpaworkshop Thu, 13 Aug 2026 16:09
moc.liamon Thu, 13 Aug 2026 15:10
jonbobby Thu, 13 Aug 2026 15:07
bookbub Thu, 13 Aug 2026 14:42
codenewsletter Thu, 13 Aug 2026 14:11
snopes Thu, 13 Aug 2026 13:45
bhg Thu, 13 Aug 2026 13:42
anna Thu, 13 Aug 2026 13:02
Newest Addresses
ibeamaka Mon, 10 Aug 2026 13:24
khenderson Mon, 10 Aug 2026 07:10
supportsolflare-gb Fri, 07 Aug 2026 13:47
support-aviva Fri, 31 Jul 2026 16:52
memoryos Tue, 28 Jul 2026 04:30
sumupportal Mon, 27 Jul 2026 05:14
threadless Sat, 25 Jul 2026 19:50
simplyrecipies Tue, 02 Jun 2026 13:23
zdnet Tue, 02 Jun 2026 13:20
bhg Tue, 02 Jun 2026 13:10
Last Read
codenewsletter Thu, 13 Aug 2026 17:27
gp6dd Thu, 13 Aug 2026 17:26
thenewstack Thu, 13 Aug 2026 17:26
simplyrecipies Thu, 13 Aug 2026 17:26
gp6 Thu, 13 Aug 2026 17:26
1440dailydigest Thu, 13 Aug 2026 17:25
mykajabi Thu, 13 Aug 2026 17:25
theepochtimes Thu, 13 Aug 2026 17:18
mydailymoment Thu, 13 Aug 2026 17:17
thedeepview Thu, 13 Aug 2026 17:16
Most Received
ail 129495
gp6 110870
jonbobby 85103
gp6dd 84478
bobby 64066
cb322c5 57069
vanchina2 56299
liamont 53727
funnyordie 52248
RSS Feed

Available Messages

The following is a list of recent messages for codenewsletter. Select one to see the content. Messages are removed frequently. Check early. Check often.

Subject Received
🔥 DeepSeek's new model rivals Fable 5 Thu, 13 Aug 2026 14:11:19 GMT
🚀 Grok gets frontier intelligence Thu, 13 Aug 2026 13:08:39 GMT
🤖 SpaceXAI drops Grok Bot Wed, 12 Aug 2026 14:06:26 GMT
🚪 OpenAI's exodus continues Wed, 12 Aug 2026 13:08:10 GMT
đź‘€ Anthropic adds invisible watermarks Tue, 11 Aug 2026 14:08:54 GMT
🌎 Researchers simulate Earth's population Tue, 11 Aug 2026 13:11:17 GMT
🤯 OpenClaw runs another cyber attack Mon, 10 Aug 2026 14:05:14 GMT
đź’Ł Qualcomm robot bombs on-stage Sat, 08 Aug 2026 16:06:14 GMT

Selected Message

From: "The Code" <thecode@...
To: [email protected]
Date: Thu, 13 Aug 2026 14:11:19 GMT
Subject: 🔥 DeepSeek's new model rivals Fable 5

HTML Content

HTML Source

                                    <!DOCTYPE html><html lang="en" xmlns="http://www.w3.org/1999/xhtml" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" style="font-size:16px;"><head></head><head><meta charset="utf-8"/><!--[if !mso]><!--><meta http-equiv="X-UA-Compatible" content="IE=edge"/><!--<![endif]--><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="x-apple-disable-message-reformatting"/><meta name="format-detection" content="telephone=no,address=no,email=no,date=no,url=no"/><meta name="color-scheme" content="light"/><meta name="supported-color-schemes" content="light"/><title>🔥 DeepSeek&#39;s new model rivals Fable 5 </title><!--[if mso]><xml><o:OfficeDocumentSettings><o:AllowPNG/><o:PixelsPerInch>96</o:PixelsPerInch></o:OfficeDocumentSettings></xml><![endif]--><style>
  :root { color-scheme: light; supported-color-schemes: light; }
  body { margin: 0; padding: 0; min-width: 100%!important; -ms-text-size-adjust: 100% !important; -webkit-transform: scale(1) !important; -webkit-text-size-adjust: 100% !important; -webkit-font-smoothing: antialiased !important; }
  .body { word-wrap: normal; word-spacing:normal; }
  table.mso { width: 100%; border-collapse: collapse; padding: 0; table-layout: fixed; }
  img { border: 0; outline: none; }
  table {  mso-table-lspace: 0px; mso-table-rspace: 0px; }
  td, a, span {  mso-line-height-rule: exactly; }
  #root [x-apple-data-detectors=true],
  a[x-apple-data-detectors=true],
  #MessageViewBody a { color: inherit !important; text-decoration: inherit !important; font-size: inherit !important; font-family: inherit !important; font-weight: inherit !important; line-height: inherit !important; }
  span.MsoHyperlink { color: inherit !important; mso-style-priority: 99 !important; }
  span.MsoHyperlinkFollowed { color: inherit !important; mso-style-priority: 99 !important; }
  .a { background-color:#FFFFFF; }
  .b { background-color:#030712; }
  .c  { background-color:#FFFFFF; }
  .d { background-color:#EAEBEC; }
  .d2 { background-color:#FFFFFF; }
  .d3 { background-color:#FFFFFF; }
  h1 a { text-decoration:underline;color:#3593FF !important;font-weight:bold; }
  h2 a { text-decoration:underline;color:#3593FF !important;font-weight:bold; }
  h3 a { text-decoration:underline;color:#3593FF !important;font-weight:bold; }
  h4 a { text-decoration:underline;color:#3593FF !important;font-weight:bold; }
  h5 a { text-decoration:underline;color:#3593FF !important;font-weight:bold; }
  h6 a { text-decoration:underline;color:#3593FF !important;font-weight:bold; }
  h1, h1 a, h2, h2 a, h3, h3 a, h4, h4 a, h5, h5 a, h6, h6 a, ul, li, ol, p, p a { margin: 0;padding: 0; }
  h1 { font-family:'Helvetica',Arial,sans-serif;font-weight:400;font-size:28px;color:#2A2A2A;line-height:1.75;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
  h2 { font-family:'Helvetica',Arial,sans-serif;font-weight:400;font-size:24px;color:#2A2A2A;line-height:1.5;padding-bottom:4px;padding-top:0px;mso-margin-top-alt:0px;mso-margin-bottom-alt:4px }
  h3 { font-family:'Helvetica',Arial,sans-serif;font-weight:400;font-size:20px;color:#2A2A2A;line-height:1.25;padding-bottom:2px;padding-top:2px;mso-margin-top-alt:2px;mso-margin-bottom-alt:2px }
  h4 { font-family:'Helvetica',Arial,sans-serif;font-weight:400;font-size:18px;color:#2A2A2A;line-height:1.125;padding-bottom:10px;padding-top:10px;mso-margin-top-alt:10px;mso-margin-bottom-alt:10px }
  h5 { font-family:'Helvetica',Arial,sans-serif;font-weight:400;font-size:16px;color:#2A2A2A;line-height:1;padding-bottom:2px;padding-top:12px;mso-margin-top-alt:12px;mso-margin-bottom-alt:2px }
  h6 { font-family:'Helvetica',Arial,sans-serif;font-weight:400;font-size:14px;color:#2A2A2A;line-height:0.875;padding-bottom:4px;padding-top:16px;mso-margin-top-alt:16px;mso-margin-bottom-alt:4px }
  p { font-family:'Helvetica',Arial,sans-serif;font-weight:400;color:#2D2D2D;font-size:16px;line-height:1.5;padding-bottom:7px;padding-top:7px;mso-margin-top-alt:7px;mso-margin-bottom-alt:7px; }
  p a, .e a, ul a, li a, .h a, .h2 a, .h3 a { word-break:break-word;color:#3593FF !important;text-decoration:underline;text-decoration-color:#3593FF;font-weight:bold; }
  p a span, .e a span, ul a span, li a span { color: inherit }
  p .bold { font-weight:bold;color:#2D2D2D; }
  p span[style*="font-size"] { line-height: 1.6; }
  .f p { font-size:12px;line-height:15px;color:#2D2D2D;padding:0; }
  .f p a { color:#2D2D2D !important; }
  .g p { font-family:'Helvetica',Arial,sans-serif;font-size:14px;line-height:20px;font-weight:normal;margin:0; }
  .g p a  { text-decoration: underline; }
  .i p { font-family:'Helvetica',Arial,sans-serif;line-height:1.5;font-size:15px;color:#2D2D2D; }
  .i p a { color:#2D2D2D !important; }
  .i2 p { font-family:'Helvetica',Arial,sans-serif;line-height:1.5;font-size:15px;color:#2D2D2D; }
  .i2 p a { color:#2D2D2D !important; }
  .i3 p { font-family:'Helvetica',Arial,sans-serif;line-height:1.8;font-size:24px;color:#2D2D2D; }
  .i3 p a { color:#2D2D2D !important; }
  .h p a { color:#0C4A6E !important; }
  .h2 p a { color:#0C4A6E !important; }
  .h3 p a { color:#0C4A6E !important; }
  .f p a, .i p a, .i2 p a, .i3 p a, .h p a, .h2 p a, .h3 p a { text-decoration:underline; }
  .j { border-top:1px solid #030712; }
  .k p { padding-left:15px;padding-bottom:0px;padding-top:6px;mso-margin-top-alt:6px;mso-margin-bottom-alt:0px;mso-margin-left-alt:15px; }
  .o { background-color:#FFFFFF;border:1px solid #3593FF;border-radius:5px; }
  .o p { font-family:'Helvetica',Arial,sans-serif;padding:0px;margin:0px; }
  .l p,
  .l p a, .l a { font-size:14px;line-height:20px;font-weight: bold;color:#2D2D2D;padding-bottom:6px;mso-margin-bottom-alt:6px;text-decoration:none; }
  .m p,
  .m p a { font-size:13px;line-height:18px;font-weight:400;color:#2D2D2D;padding-bottom:6px;mso-margin-bottom-alt:6px;text-decoration:none; }
  .n p,
  .n p a { font-size:12px;line-height:17px;font-weight:400;color:#3593FF;padding-bottom:6px;mso-margin-bottom-alt:6px;text-decoration:none; }
  .p { background-color:#FFFFFF;max-width:520px;border:1px solid #E1E8ED;border:1px solid rgba(80, 80, 80, 0.3);border-radius:5px; }
  .q { font-size:16px;font-family:Helvetica,Roboto,Calibri,sans-serif !important;border:1px solid #e1e8ed;border:1px solid rgba(80, 80, 80, 0.3);border-radius:10px;background-color:#FFFFFF; }
  .q p { font-size:16px;font-family:system-ui,Helvetica,Roboto,Calibri,sans-serif !important;color:#222222;padding:4px 0; }
  .r { border:1px solid #E1E8ED !important;border-radius:5px; }
  .s p { font-size: 14px; line-height: 17px; font-weight: 400; color: #697882; text-decoration: none; }
  .t p { font-family:'Helvetica',Arial,sans-serif;font-size:12px;line-height:1.5;font-weight:400;color:#000000;font-style:italic;padding:0px; }
  .v { border-radius:8px;border:solid 0px #030712;background-color:#030712;font-family:'Verdana',Geneva,sans-serif;color:#FFFFFF; }
  .v a { text-decoration:none;display:block;color:#FFFFFF; }
  .w p { font-size:12px;line-height:15px;font-weight:400;color:#FFFFFF; }
  .w p a { text-decoration: underline !important;color:#FFFFFF !important; }
  ul { font-family:'Helvetica',Arial,sans-serif;margin:0px 0px 0px 25px !important;padding:0px !important;color:#2D2D2D;line-height:24px;list-style-type:disc !important;font-size:16px; }
  ul ul { list-style-type:circle !important; }
  ul ul ul { list-style-type:square !important; }
  ul ul ul ul { list-style-type:disc !important; }
  ul ul ul ul ul { list-style-type:circle !important; }
  ul ul ul ul ul ul { list-style-type:square !important; }
  ul ul ul ul ul ul ul { list-style-type:disc !important; }
  ul ul ul ul ul ul ul ul { list-style-type:circle !important; }
  ul ul ul ul ul ul ul ul ul { list-style-type:square !important; }
  ul > li { font-family:'Helvetica',Arial,sans-serif;margin:10px 0px 0px 0px !important;padding: 0px 0px 0px 0px !important; color: #2D2D2D; }
  .poll-choices > li { margin: 4px 0px 0px 0px !important; }
  ol { font-family:'Helvetica',Arial,sans-serif;margin: 0px 0px 0px 25px !important;padding:0px !important;color:#2D2D2D;line-height:24px;list-style:decimal;font-size:16px; }
  ol > li { font-family:'Helvetica',Arial,sans-serif;margin:10px 0px 0px 0px !important;padding: 0px 0px 0px 0px !important; color: #2D2D2D; }
  li > p, li p { font-family:'Helvetica',Arial,sans-serif;font-size:16px;font-weight:400;line-height:24px;padding:0px; }
  .e h3,
  .e p,
  .e span { padding-bottom:0px;padding-top:0px;mso-margin-top-alt:0px;mso-margin-bottom-alt:0px; }
  .e span,
  .e li { font-family:'Helvetica',Arial,sans-serif;font-size:16px;color:#2D2D2D;line-height:24px; }
  .rec { font-family:  ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, "Noto Sans", sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji" !important; }
  .rec__button:hover { background-color: #f9fafb !important; }
  .copyright a {color: inherit !important; text-decoration: none !important; font-size: inherit !important; font-family: inherit !important; font-weight: inherit !important; line-height: inherit !important;}
  .txt_social p { padding: 0; word-break: break-all; }
  .table, .table-c, .table-h { border: 1px solid #C0C0C0; }
  .table-c { padding:5px; background-color:#FFFFFF; }
  .table-c p { color: #2D2D2D; font-family:'Helvetica',Arial,sans-serif !important;overflow-wrap: break-word; }
  .table-h { padding:5px; background-color:#F1F1F1; }
  .table-h p { color: #2A2A2A; font-family:'Trebuchet MS','Lucida Grande',Tahoma,sans-serif !important;overflow-wrap: break-word; }
  @media only screen and (max-width:667px) {
    .aa, .w100pc { width: 100% !important; }
    .bb img { width: 100% !important; height: auto !important; max-width: none !important; }
    .cc { padding: 0px 8px !important; }
    .ee { padding-top:10px !important;padding-bottom:10px !important; }
    .ff ul, .ff ol { margin: 0px 0px 0px 10px !important;padding: 0px !important; }
    .ff li { margin:10px 0px 0px 10px !important; }
    .r {height:140px !important;}
    .s p { font-size:13px !important;line-height:15px !important; }
    .mob-hide {display:none !important;}
    .mob-show {display: block !important; width: auto !important; overflow: visible !important; float: none !important; max-height: inherit !important; line-height: inherit !important;}
    .mob-stack {width:100% !important;display:block !important;}
    .mob-w-full {width:100% !important;}
    .mob-block {display:block !important;}
    .embed-img {padding:0px 0px 12px 0px !important;}
    .socialShare {padding-top:15px !important;}
    .rec { padding-left:15px!important;padding-right:15px!important; }
    .bodyWrapper { padding:8px 4px 0px 4px !important; }
    .social-mobile {float:left !important;margin-top:10px !important;}
  }
  @media screen and (max-width: 480px) {
    u + .a .gg { width: 100% !important; width: 100vw !important; }
    .tok-heart { padding-top:75% !important; }
    .tok-play { padding-top: 250px !important; }
  }
  @media screen and (max-width: 320px) {
    .tok-heart { padding-top:65% !important; }
  }
  .u { border: 1px solid #CACACA !important; border-radius: 2px !important; background-color: #ffffff !important; padding: 0px 13px 0px 13px !important; font-family:ui-sans-serif,system-ui,-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,"Helvetica Neue",Arial,"Noto Sans",sans-serif !important;font-size: 12px !important; color: #767676 !important; }
  .u a { text-decoration: none; display: block !important; color: #767676 !important; margin: 0px !important; }
  .u span, .u img { color: #767676 !important;margin:0px !important; max-height:32px !important;background-color:#ffffff !important; }
</style><!--[if mso]><style type="text/css">
    h1, h2, h3, h4, h5, h6 {font-family: Arial, sans-serif !important;}
    body, table, td, p, a, span {font-family: Arial, sans-serif !important;}
    sup { font-size: 100% !important;vertical-align: .5em !important;mso-text-raise: -1.5% !important;line-height: 0 !important; }
    ul { margin-left:0px !important; margin-right:10px !important; margin-top:20px !important; margin-bottom:20px !important; }
    ul li { margin-left: 0px !important; mso-special-format: decimal; }
    ol { margin-left:0px !important; margin-right:10px !important; margin-top:20px !important; margin-bottom:20px !important; }
    ol li { margin-left: 0px !important; mso-special-format: decimal; }
    li.listItem { margin-left:15px !important; margin-top:0px !important; }
    .paddingDesktop { padding: 10px 0 !important; }
    .edm_outlooklist { margin-left: -20px !important; }
    .embedImage { display:none !important; }
</style><![endif]--><!-- __merge_tags_in_links__ --><style></style></head><body class="a" style="margin:0px auto;padding:0px;word-wrap:normal;word-spacing:normal;background-color:#FFFFFF;"><div role="article" aria-roledescription="email" aria-label="email_name" lang="en" style="font-size:1rem"><div style="display:none;max-height:0px;overflow:hidden;"> Also: Fixing costs with prompt caching &#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204;&#160;&#8204; </div><table role="none" width="100%" border="0" cellspacing="0" align="center" cellpadding="0" class="gg"><tr><td align="center" valign="top"><table role="none" width="670" border="0" cellspacing="0" cellpadding="0" class="aa" style="width:670px;table-layout:fixed;"><tr><td class="bodyWrapper" align="center" valign="top" style="padding:8px 0px 0px 0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top" style="border-width:0px 0px 0px 0px;border-style: solid; border-color: #FFFFFF;border-radius:10px 10px 0px 0px;background-color:#FFFFFF;" class="c"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr id="header"><td style="padding:0px 0px 0px 0px;"><div style="padding-top:0px;padding-right:0px;padding-bottom:20px;padding-left:0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td class="f" align="right" valign="top"><p> August 13, 2026 &nbsp; | &nbsp; <a data-read-online-tooltip="true" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9vhLkwYtVqrPrW05H__IRtx02NHAXGwjZKUfLCrSUf3S2VTfsKs4jJBSPcb38KrbX5g43qXZDSedCuuTaCWOdBA_QA8cHAI8cEw8vzkfthidMwSXHJlPNNNdDLeaYoL0TKGKySCcCbrVTNnqVnqbZqL7prvgP7Mya2pue5G8ow2G0uTWpti7H_I-3szsoQQVyb1xXa2t1ig6KMRyQkpyfodvVhZl-pQoW4QyrVDY-jzX6CboYiz5YbUSw9innAdap3mbdCsXC3zYQXbjgSEuhjYfrr0ziEEULDqGfzEkjCNtkDDfkQZ4OWeLJ25GFOCxNSdHOrHUXmsSZbMn1QqQ3g_5oG29OJNuYyLQw7_3n6LlGXkJ2gKqOEvApTQzrMjrwWGxbLO1jCsH_oIQT6A0qERpd4wphyP3lDwLrTgaxJPoWrsZpW1j0kOMr0jHxv1F_-aW6UDNOgbI8jw7TyYd7OcgEIHhs9BRvqK4a31gt20n__sOn0hIL8JrgX75XRMEUT_plUFXitPKm7tIiOWhG_K5HX9CO_Lqgc7KUJ0AoWOkwTOMTMdTG4POVWmv93mUIXZFnFtE6hvE7JrJEHUZScDP_ePWaXLGs2b5Pbx1BeOEao7JhlI2A6gzk986OMUDe__Lv87KwFXZ0sllJPdPEkDDAZ_89MEou1031Z3NIslAIWj1vXOx9pr_wWBMn--iDQ5Shlss088dVyR1Es4bWE5UiaTMlgmAG5qo46OezjFUJCWi164tbpEp_JaSZ9Zz-LpRhRT17SB9ubeaA5T_XlK/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h0/h001.VuQ1mXjkA7FqsDWS-1RLXHpAJTLoh4ETzucVou-FW30">Read online</a></p></td></tr><tr><td style="line-height:0;"><div data-open-tracking="true"> <img src="https://link.mail.beehiiv.com/ss/o/u001.KyojDkr7Qchq5lk88rZzJw/4t5/vwXXKwJ4RBa8bnAdGR1jJw/ho.gif" alt="" width="1" height="1" border="0" style="height:1px !important;width:1px !important;border-width:0 !important;margin-top:0 !important;margin-bottom:0 !important;margin-right:0 !important;margin-left:0 !important;padding-top:0 !important;padding-bottom:0 !important;padding-right:0 !important;padding-left:0 !important;"/> </div></td></tr></table></div></td></tr><tr id="content-blocks"><td class="email-card-body" align="center" valign="top" style="padding-bottom:0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><a href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJb_xhf0L_OG-BAZuAZq71DayzUGESkECp5MaAs6kJm6VM2LPJjLVKoOfige8cuVebyYbIK6rwpSQ3UH9MH_pwDYA4qSeRU9eB1Ym-6sS_dgOQcBOEYrY-XtKvrf43fIlalwMwBWJe93HjliHw1WkJPzHzhKkvVHiqViNLynvhZp5-SxlgQNsQANu7wYB2-r0PfLG050x7a9ek4Zd68lW1H9Qkk9LHBXgfg579JIaGNEELPVIK6LtMsrpOBF9RQOT-Q/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h1/h001.tneeO_dJKc0qPWSOEZt3YfxZPOZvEA18akMpcUtQKBM" rel="noopener noreferrer nofollow" style="text-decoration:none;" target="_blank"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/608575f2-530e-4b3f-a60c-016474dac011/Group_Agentfield__6_.png?t=1786586886" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></a></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><b>Welcome back.</b> <span style="background-color:#ffffff;">Last year, a group led by OpenAI researchers dropped &quot;AI 2027,&quot; a roadmap predicting what AI would look like over the next two years. Fast forward to today, and </span>19 of the 53 tracked predictions are confirmed or ahead of schedule<span style="background-color:#ffffff;">. Check out </span><span style="background-color:#ffffff;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcG_9khwIZqiIKCbaHRBhPGytkF9TOWLC8FR8vVysWX07ItvG_Mtq1qT9NCKGo433NaEzqgQCRNfSxfuRE8xSj7BbGOyWcAjw3eiMRHu-cSlYuVc5mIF38QsPJHOlWGm1uYshgPYpn7wlc39sGANfgEQXGMoA61SxhefQWa9Hf4tdHpvR525KnEyuKk2pQCnP2gHiDAQo26Omc_ixldS8iC6oR-uwaFONOTGKM9JVc3IMogbujU3GxqNpmUKlWSByFg/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h2/h001.6GKiT8C56tDXf9YHodhNEXPoVWMt0smqEeKuv1_YBGo" target="_blank" rel="noopener noreferrer nofollow"><span>the full timeline</span></a></span><span style="background-color:#ffffff;"> to see what’s changed.</span></p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style="background-color:#ffffff;"><b>Also:</b></span><span style="background-color:#ffffff;"> A detailed guide on harness engineering, fixing your home wifi with Codex,</span> and how to humanize AI PRs of your dev team. </p></td></tr></table></td></tr><tr><td height="8.0px" style="line-height:1px;font-size:1px;height:8.0px;"> &nbsp; </td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:1px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:4px;padding:10.0px 10.0px 10.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:125.0%;"><span style="font-family:Eczar, Lora, &quot;DejaVu Serif&quot;, Georgia, serif;"><b>Today’s Brief</b></span></h3></td></tr><tr><td style="padding-bottom:6px;padding-left:0px;padding-right:0px;padding-top:0px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ul style="font-weight:400;list-style-type:disc;margin-bottom:0px !important;margin-top:0px !important;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><span style="font-size:16px;">How Databricks manages AI coding costs</span></p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> How Apple could win the AI race </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> Save token costs by prompt caching (tutorial) </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"> Field guide on Grok 4.6 (cookbook) </p></li></ul></div></td></tr></table></td></tr><tr><td height="12.0px" style="line-height:1px;font-size:1px;height:12.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#3593ff;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>TODAY IN PROGRAMMING</b></span></h5></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><a href="https://link.mail.beehiiv.com/ss/c/u001.tgWOPLtqyPb9_0gOXDT9L8lXzZqH1EnPOhoek5BweeqStK5CLv7t-xco7ZnzzwMUR5TbkbaVhE7Q-XHwxphnP1Gpvw7uAuVljsRhljOfBlShyw5fehYu3XfctqDMdVXAyHUn65vmOZcQvrXACMce8XoGh8ikqsAI6HGVBaTzpjzIjbV9rZvFvP7ptMMtC3JNVeg5Gz05neEiwG8wPut1AWOghmNG6ry98nAxq43puLELjOBVoEMBXBx7aIwKSMCgvaqrM55PLoiYmv7a_QX90w/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h3/h001.ywoPuDz1Qwh30rMhvqbPKa5FmoXomNxcJinyFd2lRYA" rel="noopener noreferrer nofollow" style="text-decoration:none;" target="_blank"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/215702da-08df-4444-a965-d504b6de4300/Thumbnail__6_.jpg?t=1786623024" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></a></td></tr><tr><td align="left" valign="top" class="t" style="width:670px; padding: 4px 4px 4px 4px;"><p>Click here to check out the specs.</p></td></tr></table></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:1px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:10.0px 10.0px 10.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><b>SpaceXAI’s new model targets long-running agents and large codebases:</b> Elon Musk&#39;s AI lab just unveiled <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.tgWOPLtqyPb9_0gOXDT9L8lXzZqH1EnPOhoek5BweeqStK5CLv7t-xco7ZnzzwMUR5TbkbaVhE7Q-XHwxphnP1Gpvw7uAuVljsRhljOfBlShyw5fehYu3XfctqDMdVXAyHUn65vmOZcQvrXACMce8XoGh8ikqsAI6HGVBaTzpjzIjbV9rZvFvP7ptMMtC3JNFK2birOMMeLnRt9p2pcgSuwrwqnmdqySyr3HQeS-TN8U4kSuOypXF2zmqypat_TYVRqoZD90-7Ucyv4_-s3fcg/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h4/h001.C4nP0FMYOiTTSmVKzt50ifJeEHFHagNk6k7zUPCsKSE" target="_blank" rel="noopener noreferrer nofollow"><span><b>Grok 4.6</b></span></a>, a model specifically designed to handle multi-step workflows. Whether it researches a codebase, structures an app, or iterates based on feedback, this model performs reliably over the long haul. It’s currently available via Cursor, Grok Build, and the API at a rate of $2 per 1M input tokens. Devs are already giving this model a shot. Shopify CEO’s <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcH76istm2gmEd8BIEP9vxxfQGlaHLvH3VlR79IqOqiZzAoK6fVlnQ79yGavrmyMsLuIJPKEIZEmSKNm8EuYi40-LqMtfZOijDxjBgXt8Kz6L7k9Vrl-uJagB8lFW3V0OoUYOYG_09CEZwkBIvvfbOxafnRUukSjLuEEKw4wguHDncrtSerNbe_qNNAVTybsyAaS4VTTPf5siv2dk19wEvU9yqtsIY7I2hEdMrOurlXDGZ3ds1xHct2i7zeg1s-0UtE/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h5/h001.wWZ5yFkjwJbuOkF_iA9Bf2_gRgems24omCn70XzUGcM" target="_blank" rel="noopener noreferrer nofollow"><span>post</span></a> about the model&#39;s animated reaction during a maintenance task is making rounds on the internet.  </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><b>Alibaba open-sources its most powerful model to date:</b> The Chinese tech giant just dropped a new version of <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.nWZojHskIfWq5w8Zm9qW7papiNOz3BriBrbnPlDyY60H9xRKRLqIWO2m7PuRR7240n-n7yfJdUYF4zn4ujyxtd1Nl5_sh30D4nisCIg98YPijYwdkcd7iF2IHTn94pgoC2mPy-1T5flv9kAFALXA4RnU3-gVTd7af3wLsHlTFRig64sIOLG0M61yubVmq3zWCmjKbFR7jnKQv2iB_qKKCrZUxL7EExMFuFpIw-30j3Jj3pTX5VPap1OIMnCC0JFx8kFHYBldOdFtR4phZQrEr9Esy74JB7LM_IHODlnOlxs/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h6/h001.yx0CSAYsFNnnezLd5i-c2-HRx0FjSL7lQCxtTsJLlq8" target="_blank" rel="noopener noreferrer nofollow"><span>Qwen3.8</span></a> on Hugging Face. The company claims the model goes head to head with the top frontier models on coding and agentic benchmarks. But there is a catch for devs: you will need a massive 4.9TB of storage to run it at full precision. Even with <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.WqBfFAvShDcli0SZD3O4YtO7zhiU3upCoTIEdt-aT2rwudNsPtsA5nesYN1t_cWMs2sZl19GLNrp1wOT7Vxg_Cuk2xVZlIgz8EP7zCEkvaZLvq-GfUXkaT8QjHT8Zn-3log9zZl0YA41QejRPpaefRo2RI0GvST3_mlVUSDuRWf3eQ9N7xO5Sq00fv2K-Xvmz316kIfAUwVb3aD5QYDmP-ZEhbzurpn_xcv8M79_rq_oGSdtqzxNh1OrqYGWO0IDZp_yIurQpdE4h2tif_Zcng/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h7/h001.Kah0RrN4aK9EXNlWxYJzrNIqPAmAi-a8WXIuosvTQKM" target="_blank" rel="noopener noreferrer nofollow"><span>Unsloth’s 1-bit build</span></a> (which trims that down to 397GB), you are still going to need some serious RAM. If you want to run this locally, a lighter 27B version will drop soon. <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.pljPPsurrJ8ITcFAp15gISDAeD4fIJ-lxbf_RP6HCmcNEasR_6URYgvqahmg0Uy5M07zyvLwSh9mfvazSwGdEo6sOn8T4vhnAQ2LK7tmSiH3SqvCm0G3xmJ0bC_IGKjZjgyS55C5cc85q-kBA8Gh3kp6sbFlgs-UKnM3zV8iRRyrRFIFNYAs0te1YbYnB8cY8MavqkL3evjza5v7JqZ7X82L2F7LMMPiXBIRpMITfhf4r51yMxsjJXrhvlH-sXF6A_Wn-KlrCviHvAdR6rHcrLiqXKy_K81VTqSX-Hy8ZMM/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h8/h001.SY6sFDDHZJgcIz1rZ_Re8KblskB5vxP02IZ0YM0x2xI" target="_blank" rel="noopener noreferrer nofollow"><span>More details here.</span></a></p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><b>DeepSeek&#39;s flagship nears frontier coding at a fraction of the cost:</b> The Chinese AI startup just moved <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcE_1qFWGAfc5ZpYEwy76x3NoH4d9LW3AyD7FNOc0nFgL4rV7WU9_9k1omiuvzZGWCTf6_T49OPvmvRQ2Y6msq6TcDjcIGdy6Im3ktl9r5ONhYPYMx1j2DqthyQKoppMYyykWsPLb0KLlBCAie7lwafKA3LKJKxvCE2dxrB7_xfmVN0jbn0qkrAVIDlDnV1EvzgRqRtVnp10WYz_IKPkIqTTiDE5HvilFG4JqC5uC6So2lgv9wLFEzOhJqwFHDqEC_U/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h9/h001.T8Rk6qeZmLQi5Dz10te2C3qppX_k8k0AmBYI8ivAZLY" target="_blank" rel="noopener noreferrer nofollow"><span>V4 Pro</span></a> from preview to general availability while maintaining its current pricing. It costs $0.435 per million input tokens and $0.87 per million output tokens, which represents a small fraction of the Fable 5 rate. The model supports a 1M token context window and tool calling, allowing it to integrate seamlessly into your agent pipelines. While it still trails slightly behind Fable 5 in agentic coding performance, these results come from the company&#39;s own unverified benchmarks.  </p></td></tr></table></td></tr><tr><td height="10.0px" style="line-height:1px;font-size:1px;height:10.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#030712;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>PRESENTED BY AGENTFIELD</b></span></h5></td></tr><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJb_xhf0L_OG-BAZuAZq71DayzUGESkECp5MaAs6kJm6VM2LPJjLVKoOfige8cuVebyYbIK6rwpSQ3UH9MH_pwDYA4qSeRU9eB1Ym-6sS_dgOQcBOEYrY-XtKvrf43fIlalwMwBWJe93HjliHw1WkJPzHzhKkvVHiqViNLynvhZp5-SxlgQNsQANu7wYB2-r0Pfs7CYHyjwMbEpJ0nO4Our9_iDt9hwueZMAKY3UAsdQBgpQNKqcByRrVD-w0ygPIqg/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h10/h001.bQFGlzmHzIjzpS_SNAtEg8EDpEJhf-QAQs4Sp47B37o" target="_blank" rel="noopener noreferrer nofollow"><span>Open source hit frontier-level code review at a tenth of the cost.</span></a></h2></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#a1a1a1;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><a href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJb_xhf0L_OG-BAZuAZq71DayzUGESkECp5MaAs6kJm6VM2LPJjLVKoOfige8cuVebyYbIK6rwpSQ3UH9MH_pwDYA4qSeRU9eB1Ym-6sS_dgOQcBOEYrY-XtKvrf43fIlalwMwBWJe93HjliHw1WkJPzHzhKkvVHiqViNLynvhZp5-SxlgQNsQANu7wYB2-r0PYB2OYNlM4nXJnvsXtDF38Rtsr1SeHLLG2fE5BQaPtv6obypM3iHqWYJrZ8FX9hXiQ/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h11/h001.bCM_yTOMO9k1olRcZRj6WqflkYZRo9-FGj47cCwAABQ" rel="noopener noreferrer nofollow" style="text-decoration:none;" target="_blank"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/a8bd2252-3c0b-4d2a-8b3d-238db94e04c3/thecode-pr-af-podyum-1920x1080-100k.jpg?t=1786586957" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></a></td></tr></table></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-left-radius:0px;border-bottom-right-radius:0px;border-bottom-width:1px;border-color:#030712;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-left-radius:0px;border-top-right-radius:0px;border-top-width:0px;padding:12.0px 12.0px 12.0px 12.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> An open-source reviewer now places #2 of 42 on Martian&#39;s Code-Review-Bench, ahead of the commercial tools, at ~10x lower cost per review. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJb_xhf0L_OG-BAZuAZq71DayzUGESkECp5MaAs6kJm6VM2LPJjLVKoOfige8cuVebyYbIK6rwpSQ3UH9MH_pwDYA4qSeRU9eB1Ym-6sS_dgOQcBOEYrY-XtKvrf43fIlalwMwBWJe93HjliHw1WkJPzHzhKkvVHiqViNLynvhZp5-SxlgQNsQANu7wYB2-r0Pbxsjwpqn6cO-nHx9iU5nFNCD1M0rXALvIkarfZenOrxgeCB6AAP1Av3HgBPzaCSEA/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h12/h001.AYQ2uO0YkqQSt7qZygD9qHmzaWyJhUGWNGdlZ6SwHFI" target="_blank" rel="noopener noreferrer nofollow"><span>PR-AF</span></a> plans the review per PR, runs reviewer agents in parallel, and verifies every finding against your source before it posts, so no hallucinated comments. 0.706 recall, roughly 3x more valid findings. Apache 2.0, self-hosted, runs on any open or closed model. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJb_xhf0L_OG-BAZuAZq71DayzUGESkECp5MaAs6kJm6VM2LPJjLVKoOfige8cuVebyYbIK6rwpSQ3UH9MH_pwDYA4qSeRU9eB1Ym-6sS_dgOQcBOEYrY-XtKvrf43fIlalwMwBWJe93HjliHw1WkJPzHzhKkvVHiqViNLynvhZp5-SxlgQNsQANu7wYB2-r0PRUPs9kEj27YQkGVsoufH19zDUrPQkY-gS7aVqayFsG0faPMPPqvWbBUVkTyW8fg3Q/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h13/h001.mlH679gWadGZZAsuLAGql5-HnmK9S1_o8OXYNGq1Pco" target="_blank" rel="noopener noreferrer nofollow"><span><b>Star & Deploy</b></span></a></p></td></tr></table></td></tr><tr><td height="8.0px" style="line-height:1px;font-size:1px;height:8.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#3593ff;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>INSIGHT</b></span></h5></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:150.0%;"><b>So your AI coding costs keep climbing, but you cannot contain it. Here’s how Databricks manages it:</b></h2></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/9167cc65-65ec-4d42-b4f9-293065318fd8/Thumbnail__4_.jpg?t=1786612863" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="left" valign="top" class="t" style="width:670px; padding: 4px 4px 4px 4px;"><p>Source: Databricks</p></td></tr></table></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-left-radius:0px;border-bottom-right-radius:0px;border-bottom-width:1px;border-color:#030712;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-left-radius:0px;border-top-right-radius:0px;border-top-width:0px;padding:12.0px 12.0px 12.0px 12.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><b>The wall everyone hits.</b> Agentic coding can help your engineering team ship up to 10x faster, but the costs can spiral even quicker. If you aren&#39;t careful, your AI bill will eventually outweigh the actual value it delivers. Databricks calls this a solvable engineering problem. According to their internal playbook, teams that successfully manage these costs lean on four main strategies, ranked here by impact:  </p></td></tr><tr><td style="padding-bottom:6px;padding-left:0px;padding-right:0px;padding-top:0px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ul style="font-weight:400;list-style-type:disc;margin-bottom:0px !important;margin-top:0px !important;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Lean on lower-cost models.</b> Start with the cheapest model that clears your quality bar, including open-source options like GLM. Most everyday coding doesn&#39;t need the most powerful model available. This can cut costs by 50% or more. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Route work automatically.</b> Developers shouldn&#39;t have to pick a model for every task. A smart router can send each job to the cheapest model capable of handling it. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Swap caps for friction.</b> Hard budget restrictions should be a last resort because they can punish the engineers getting the most value from these tools. Instead, show spending in real time, add warnings for usage spikes, and quietly shift work to cheaper models when necessary. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Trim the context.</b> Even the cheapest models get pricey when you&#39;re feeding them too much data. Honestly, most of that context is being added by your coding harness, not the developer. If you tune your harness and cache settings, you can pretty much cut your generated tokens in half without seeing any drop in quality.  </p></li></ul></div></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><b>The starting point.</b> Combine these levers, and unit costs can fall by as much as 90% without a quality hit. But you should start small. First, look at your team&#39;s spending, identify the models and tools driving the bill, and then tackle the biggest source first. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> P.S. Databricks&#39; full <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.AtRzLqL3EQmRcf6rV4XqutsrSwrlXUa4CLXik5r8lE312PLNpo3IlXsaZLW33zaDKpc0t_CNYY4jneGPffhWuKxPCCD3ZgMJHnEgYAPCoBk9rK5lHj4FmGbVSDK8Bx0ckdLMZt72bGRaw0T2Pf5vFQVc_-UV7Ntoesh0ZxRKvV0nzFEqh8dDnGP3G_mkSBt1yRNt4fA4xuYDW4v43y40EoXdHvxq4xJsNuEVeUSLy22m3_wsXxwl2cyessghNK7MgxWvErsdvpDLCmhgI8j-956hQrIy-Riob3dczYPX2fwDz6umpofqV-Ix8SZRrVMp/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h14/h001.gkdfRjntvj4AfN91C4U-FFrX1OTmTwZOGfQHUcnH0VQ" target="_blank" rel="noopener noreferrer nofollow"><span>walkthrough</span></a> covers the tooling, while its open-source Omnigent <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.IFKgnKhChLEORPQcgirN7IjeiPCaZwpNvRGAs8xtsc82H6x18cbNqRd2AmbrUt2tX7fSUoFBivFuEtZJ6MF6-m94kBeA53GY6ujeE0YEft3hFk_FNhFzRyO9tx0vwKPtw9_nuPFQMB_TudG8DdFA0x36vNTcg6BCmg2C5-6_5jGFymBA2F_66CvFIwhUJhAsVnmyBzdeYAuvEbwJCUVTN6fWX1Xu08YBNnDmmFUWoxaTKfVEoHjbWEr1v3tLoVpb2PK27HT8OBxFLD93q-sZlsb_1jFxXmyIaYLhqgjyU4U/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h15/h001.5Xl-2CpR4gdL8Jo27HSp6FXrsKdszJq-PcRjrMxECXI" target="_blank" rel="noopener noreferrer nofollow"><span>meta-harness</span></a> lets teams experiment with model switching themselves. </p></td></tr></table></td></tr><tr><td height="8.0px" style="line-height:1px;font-size:1px;height:8.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;border-radius:0px 0px 0px 0px;border-style:solid;border-width:0px 0px 0px 0px;box-sizing:border-box;border-color:#E5E7EB;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#3593ff;font-family:Eczar, Lora, &quot;DejaVu Serif&quot;, Georgia, serif;"><b>OPINION</b></span></h5></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-left-radius:0px;border-bottom-right-radius:0px;border-bottom-width:1px;border-color:#030712;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-left-radius:0px;border-top-right-radius:0px;border-top-width:0px;padding:12.0px 12.0px 12.0px 12.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="e" align="left" valign="top" style="padding:0px 0px 7px;"><h3 style="">Databricks showed how they cut AI spend. Where&#39;s your cost coming from?</h3></td></tr><tr><td class="ee e " style="padding:0px 0px 0px;"><div style="margin-left:0px;" class="edm_outlooklist"><table role="none" border="0" cellspacing="4" cellpadding="0" align="left" style="min-width:300px;"><tr><td style="width:100%;border:1px solid rgba(50, 50, 50, 0.17);padding:6px 12px; border-radius:4px;"><a style="font-style:normal;text-decoration:none;" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9sHsW6DwOSVHpiQI5sttAo88KaZ1eIBZZ9V9bj8cmMWZgtgqJtV5WTdUOBEq6N___t500R1EDn0klQJWvt8YddoLPk4o9FHyFjBCpTox61v0pVxcQK8Tu_1Ei1vwx7jFjkiHfTMFGTglXOfrBYxrwhULdM6Yl3rIJ6hJdXmZLKUeRBkFCeUdH8mpKVUt36uZY1FnY9aRXH5o2q0r2Yy9nfocSutyFb7SGSF0thU3ywN-QVsUFXRxnHnAABJMmWdQym5Hv8ESLifTHF0ufr1Bt9yo_0ObmlmgaL9oF7nanuYstaiNfXfepQujNJe_qWDVLwf9oBNY0XaKDFkNJ9mypvFS9Vs33kLJoNVJQdTw4nMuR9U2BossKpDCy_lNU76ed4UWFNebOphSMaI7LiPTniPfSSJdcZbrSjP1tg7Qn4_nvdO1c_y_naWfVDNsMwXeW6PlmyUeMdmZnBwP17DTkZY4REXBNCoQLFOfJ_nzojdRWqYB53ICb_IOM8a8lMbBitVOD3dabsoid8p5pnwAnbKwVYAGbDZ8bSfh0f826bl_zbm8vfOZtLZumcR83B3k3KsapbKCxVydStndmu40q40T5BB5VAf1ioAbXmN_bci23ANZIe9xJ1nxEV0QfQ6zJ2zk1tgMs_PtlZ37f5XEd8Krkajs27njtxHihR7QO-ilpTkMetiM-PGg1_i-QKCQS4_7SxyKD0VK23qw_93yMm9AQOdencN4mP0kDw2cSvwVQdihOH3jKtQprD7i6419_7bQxjLlfLKiLUZmxk_qRnGIF6m_8pApsqAInaF0Qs6rCNpjOZpgmaLDVK42IB7Qd7fythzbxgemQj1py2X40_1ky6BISczwjOu6ejf2tksAyOANWh73YJMWlnDrePOIoSP8wZUhDu0w8r6jKT-6P5-G5LjDlhpAB_x0f6hoim2BTPjK3q0qhmAog6IGv6ppIOdOqO_TCN4jHAd5eNE3qmQ82KIjSfirPyjgLkYzQ8qkFlZtzDH49f0_0Ag9vsgxJY/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h16/h001.KLeNVrRqtw0pzyoMpwkUh1ECmiZhhpIJr2YnXWdEmPY"><p style="font-size:14px;color:inherit;"> Devs default to the priciest model </p></a></td></tr><tr><td style="width:100%;border:1px solid rgba(50, 50, 50, 0.17);padding:6px 12px; border-radius:4px;"><a style="font-style:normal;text-decoration:none;" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9sHsW6DwOSVHpiQI5sttAo88KaZ1eIBZZ9V9bj8cmMWZgtgqJtV5WTdUOBEq6N___vweLGh1f7Hk-UOl0TW1wmf_wEDt753CR33dl0_QnNkMcOtZkD53AT4_yQBFKzMEysFOcNKtaf7mhUE8fV2gpxRJfqztg6qhKRgNuEyQoRr0dqeS8_JqVHKXODXQMTWJaoxjjgM4EWcBIQuD2GnQf_hhZ_xr46xzowEiAJeIPmANg-_PLUnknTKvz2fckrPUuBtDo9wjb9IZTQUc-TjMIt1iy2EYTl0v5yQf3IrZnLMD7JbOxtCh-1NRedlRaRlVrnzh6TGOLcLgXf8Ihrg_gJuJzpDyQzAs_MSytcbXLcT5IsAJJQZ79ja9AIs374zacpaOcReaNAR9_wDdTUL9sw_2TvAUiHGvdeKxCR7UdHYIoBhzaN8xUlEJd9aFWtYJIiHEU3zZrij-qwj50qc4DP1X1shGNgdrbxX3dw9R89XIYS2bHa_ZCtu0jXdsQ7u4ALIYcN63ZQ7D5jnh2STRObGSsquiPxmt67YibQE3HQXPUBXjXi_tv7dtIvBoQAK1EXvYHHwVIhNJhnP-ubbKeA47xEvEsu0aTl-yfUvTwByWzFlO6PahqIfvaw6IWQCX7yVd_nEpSBXWuKQKSA7zeVlTu_xkzZ3Dbt8eav5eMBcMr9jKj_G3cV3i67XGf6smWpAew7Rd3HTu1AUXP9gXpaQfYCGVAuDNUMZga1hYFaHlSzQd0mJLSlUMWVVvs2JD60PGEKuFOBQRmHyD1UESSE7tckIST6AwI3d0_f_uOLPlO6Yt5bsuF55BAbP-A2cPmjNucqi3578nR17cpklnAdsFucunBulcXZVd_x2l1PILAdTLwgbqUpEwvgJoY8i3mUfORI6MkJyvSeX2aTcGqrW9iN4zGqHrNFItEZ-2JvzJ0Y1M-Mnw9GC2Rvo7jtbxYkD72v-i-5LuF68kSKXdEJXUVTFoy-ny5U5MNdMkqKXeNSKiwoZf6rRDR4mFcDlt-E/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h17/h001.0640U2lgiS2R_UcDpeWIpUYCfEU6ME_KNXQM9X3BUM8"><p style="font-size:14px;color:inherit;"> Agents burn tokens on bloated context </p></a></td></tr><tr><td style="width:100%;border:1px solid rgba(50, 50, 50, 0.17);padding:6px 12px; border-radius:4px;"><a style="font-style:normal;text-decoration:none;" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9sHsW6DwOSVHpiQI5sttAo88KaZ1eIBZZ9V9bj8cmMWZgtgqJtV5WTdUOBEq6N___v6J0-wUO_r6aogpUMSt8qFgvH0jY3T_eqdX-Oykmkj7YC6jHrXcFjMHeA3cid9utDBMdwi6l7AQM95c9pxJwluSoC4xBOznzt2rvIU8mtw8_KVkI-szND6Z7nhEARQjjBndd7o94dekHbPUiJRW1FHLM1tGz7H-zZUchQeDdCFm4cHP1I7I7Ur27RPp_QE1KYOnzSzB6cGClkmBTTdSDGcLxgKm3JPynHgEuvVAOSttF8hEn_6MD0oaOU1yV_IOQ8ulr2EyMwEfrjekEcpNBawly5NgCzd2klXbuDiN2nWcMfyBo2_7MFpaTGK5NC0_1EwQP07t7EIoD88O2TstkY_C9dQBKeNZJcvefEcdUbaOK4TkeRp2jX74KeLfozH-l6PCBasI0q9swcctC_HpKS-Sc-Yt3TB_Ge358vn1PgvOrAZyo5PpIoqlJKH8fGsgIp0CVWbVFPnautSw3MLNkHE9rve0n3Hgblq1tfiN0Zv-vW3WX2AoeB0n1vC2wGzxExoybBbIFDU7z2RJ78cqfqeBGEN2Oj1OpGNjChoHla6axHhsxFv69CpO2kGHYt6JauUQUR6KaG-411Qa3mcjJ77lERA_B32vvTYSEj6_9i8BUXxbUpBd7W13JZsWzWcp0a-jdxvhJPV2cYkiZlKdOCBUE-dvL3WpF1k14sIzxWlqOVqldss0_dmAdd4Fd86Hh71yzQne6COZbXTmvvMxo2fuJQ9tjop1YNypI7UVy4kmV3taMsBsvrBV8-D01TLckF0hwEkUFIEs3VnZtfNXLJ-nWf9VHDmuLJ4tLD-Z2rXpXKIOiqCsoCA4Lnty7gKQHsBYg8jTGt9p2FWPuDOzxyDKpwo6M8TRggsJWISI97w41otTu03fEcjmAUiiGBHTDqdqpl44iegHCjjDpJYTibXcO-NssDiXYeJQFwovSzUUxgSjirEdXmgjFDsDOuT4j0/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h18/h001.ocv3azyDumi7Gxj24cwIuTfSth1Rs7M7n5Hpb5whJIc"><p style="font-size:14px;color:inherit;"> No visibility until the invoice </p></a></td></tr><tr><td style="width:100%;border:1px solid rgba(50, 50, 50, 0.17);padding:6px 12px; border-radius:4px;"><a style="font-style:normal;text-decoration:none;" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9sHsW6DwOSVHpiQI5sttAo88KaZ1eIBZZ9V9bj8cmMWZgtgqJtV5WTdUOBEq6N___ugQcoP2f_NLzi2hKd3rqqYvNJapKA-uofKJlVeZyI4fTAU0UGwdOdlFCsUNeUUOudd4kRDZf0Uc-9RtZHGxTCyaoZwiLIfAnNl4Kl_3xTxAUfG6l5R9uLmgKS_uCg6_sWwpRmf40s0JCxjpr2ZId486gqoSoI24wyaqgthJWSeb1j7I4Q6x3HdxDGgbwASwptOlnlxOiPA_3JwC-cp9QIJf5wksfPdkQfuORRevqg3VhFahRVOvNTvgpvHEaAapC6PoEy9B3OPQEhbvlaYkkAiE8G7qUN6YXRMDd3JCBxuuZ81BSGw2dW-o58TEIieulcfmgQ3raJmj_xHZk8VLPN75FQxW_XBi3kba99M2rdtk1wwiMVK04hg8Tqh8Rr8OkyK6W6r631xDPk45FckdgupUiPSxEOkSi_OGnoaG4ZtzSWcwk3afK2Sp6FBIMYkLD59URrlr6NN7FsAHbqUG-rRRACt_1APudBqJfrTax_TTDnEOhnPlZPNToza-w870s6vQOQmM_ZuXofd5mUrvVA87ZQqV9cRi4QR7Xu4NJYqWpfMiBzOSFqCqdTOLdn9Z2yIfFxrzjaEbokRziYSZlOusUX7yf9qYHVk44FASSzJ5RukPfIb_CZY5jpCH5vxEkSvr92lru4XikwsGjF72dpmH8ks5IhktGqiGE7I_fq4aXQt1g76-mL8iFW8MiX64aF2nY49yec5jwtRlWJiPt7hIUhqOmY7AJrZ17xztDbhIZJ-zDM8Gm4JFdyN-_3J5-uf3SpPBiFMAHZyYgVX_PfackzaC0a7j7cJYw4UImTaYjYCtSdFJztCD2Zm1WWhLqb_esI1FHrkhe1O0q5py8iVJTmFs0dkZ6yuGjsF--ZpXBW9XOs6wjk_2v7pkoHCLSH6-xDV1R78oMxI3tpdl80lmq52jhwZqDG2BkoguRCdjgW85i09GwxnmjF8ukbPdEk/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h19/h001.mWsRgdxQmWyOziptiAqHHmR2n_7iMd5c0XzA1OVkmw0"><p style="font-size:14px;color:inherit;"> Nothing&#39;s wrong, usage is just up </p></a></td></tr></table></div></td></tr></table></td></tr><tr><td height="8.0px" style="line-height:1px;font-size:1px;height:8.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#030712;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>PRESENTED BY SONIOX</b></span></h5></td></tr><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.lj8E5PmaCEQWZtY8yZ5P0kPTDHJrqJ52iNF1Xgp1TE51V7T8BAXD4k1EJeIgAJu5_e05TpPNNL2rh9cvi5eJVNT8sysakRk0SbFr84-I0KPUW3K-5H_qBvzLz4KKxiOwkxN9JRbJ3IxxnutgTDbIEg/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h20/h001.HuClIb0R_91WWoDZU7F8P4pm7mEuyv6FTikh0PgXakQ" target="_blank" rel="noopener noreferrer nofollow"><span>Give your product a voice worth listening to</span></a></h2></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#a1a1a1;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><a href="https://link.mail.beehiiv.com/ss/c/u001.lj8E5PmaCEQWZtY8yZ5P0kPTDHJrqJ52iNF1Xgp1TE51V7T8BAXD4k1EJeIgAJu5_e05TpPNNL2rh9cvi5eJVJZvURdFTi9GzOEi8BHGl1aGcz_2jqQ4TISZsc30RfDa5F_Sa9AwiDu1vcjBa9oFAg/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h21/h001.i3zswrux7XBCfarA9zUKem5RlFY9IgsAhaXF8LJYQi8" rel="noopener noreferrer nofollow" style="text-decoration:none;" target="_blank"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/b0daeeed-b488-47f6-8a4b-8142a3a5d3f7/The_Code_Feature_Ad__5___1__-_Slava_Obukhov.jpg?t=1786538400" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></a></td></tr></table></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-left-radius:0px;border-bottom-right-radius:0px;border-bottom-width:1px;border-color:#030712;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-left-radius:0px;border-top-right-radius:0px;border-top-width:0px;padding:12.0px 12.0px 12.0px 12.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.lj8E5PmaCEQWZtY8yZ5P0kPTDHJrqJ52iNF1Xgp1TE51V7T8BAXD4k1EJeIgAJu5_e05TpPNNL2rh9cvi5eJVFJlc_vwZ5WB9EaIfuNLPBFjC_PfVDPedKtHaMV0uAWEUiZzbD_hYfo-k5IJ07ojCg/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h22/h001.MqFZtWKAdDLfj68FO6v9hXpUFCpDoPdmpaDFWYh-B1o" target="_blank" rel="noopener noreferrer nofollow"><span>Soniox Text-to-Speech</span></a> lets you create extraordinary voice experiences in 60+ languages with expressive control, exceptional precision, instant voice cloning, and ultra-low-latency streaming. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Direct whispers, laughter, hesitation, excitement, and emotion, or precisely speak phone numbers, email addresses, technical terminology, and multilingual text. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Built for voice agents, global products, customer support, media, and any application where speech needs to sound human and get every detail right. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> $0.70 per generated hour. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.lj8E5PmaCEQWZtY8yZ5P0kPTDHJrqJ52iNF1Xgp1TE51V7T8BAXD4k1EJeIgAJu5_e05TpPNNL2rh9cvi5eJVJrQwdaL62w2DvmLErCOOgC6PI7AYcJ9Tycv3H4FguYYDs0FgT4zlXK5x8TvAiFlhA/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h23/h001.UyXcvsaDzSuiJthzLX8OEXAd-mWf7Aqknxp6ocsPDq4" target="_blank" rel="noopener noreferrer nofollow"><span><b>Try it now</b></span></a></p></td></tr></table></td></tr><tr><td height="8.0px" style="line-height:1px;font-size:1px;height:8.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#3593ff;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>IN THE KNOW</b></span></h5></td></tr><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:150.0%;"><b>What’s trending on socials and headlines</b></h2></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/25632e7b-6e42-4d5e-9ba0-8d0fb9757857/CleanShot_2026-08-13_at_15.52.53_2x.jpg?t=1786616612" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr><tr><td align="left" valign="top" class="t" style="width:670px; padding: 4px 4px 4px 4px;"><p>Meme of the day.</p></td></tr></table></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:1px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:10.0px 10.0px 10.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td style="padding-bottom:6px;padding-left:0px;padding-right:0px;padding-top:0px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ul style="font-weight:400;list-style-type:disc;margin-bottom:0px !important;margin-top:0px !important;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>WiFi Fix:</b> A tech CEO pointed ChatGPT Work and Codex at his patchy home WiFi and let them troubleshoot the whole thing. Here&#39;s the <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcG5RvSVIY9CzfZr0epQUfDe1dRQEa8gmTqJo7falWLLAskzD0Tk33kVGh6G76Fo4tg3GRHREOumniS4-nOwX_9_vrMJ3_E8rYiHR3UFHyGUIbRIFKQR3X5pnvIKpQoHDZOYN-LUzt_od3Rf1ZaHNag0xVuBoq_03XjdHPR9rLg_frT80sOHBUnzlLyA_uCxcCR2sL720CGndEE8Xd_4vjcNAE3iKsKL4XgoS8kRvLRCPtTZUiJBUy69jRd454ohWoU/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h24/h001.yMBIyPjAjaeFeZyDGBCWzuWXS-8973aME6yeFd0h06U" target="_blank" rel="noopener noreferrer nofollow"><span>prompt he ran</span></a> (3.4K bookmarks). </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Apple&#39;s Play:</b> While US companies burn cash racing Chinese AI labs, this viral theory explains how <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcGYiCUsEDtAi2Xo2mFcUBm4NOYvpI2e22BmepWET57YkfAputJ9lZc-fWiuqLwnY05HzTT96gMmWFzkGmGd_xvBNttbMQ9sHbD8UDSHcI3g10PO2-VCje3iSIfIp5Jk_-5ud8fKiJODp8ktF0n3CXre4v51tf3sVU-pvm94QA3prgAKp-idHnelTpk6faqdOROQa3XojtrMwPze-TvJ0kPGoyjlPQlnZYIxY1BlUMAi6MpupBTeRTKdnriH95CABBQ/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h25/h001.vdyYMKAAIe6z4OlG5Nuzl6gtjMcUTrT8TzRWcGcB3aM" target="_blank" rel="noopener noreferrer nofollow"><span>Apple could win the AI race</span></a> without ever building a model (574K views). </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Fix AI slop: </b>Ever noticed how AI-written PRs look polished but are actually a total mess? This post <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcHqwYRRvDDdbnR7YLjtCf3I43jzd-REDVE35qkR_WqpteTHsKz75Nb9SpB0RaaLJjoZLuhvC6favNMP4U3E-K2o6SpRNpdJd0YCcsyMtAo-ToM_zZdLcV6dLtxVxRd7aD82LPm4BS6hUYDwEo66PUXE_K3REJcQoH4y7JVkOlD1EYiNhxLrU3_ePcsQHQGJI8S9tYpPcMFNLBchIIU1D3bOpRuChKUGCs_oIzydizhVWLqNX2w7D3loCU_zQILqNow/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h26/h001.4JLki4imbB35BChSZj7ftvj9k64UmpmXevb6IqKlnRY" target="_blank" rel="noopener noreferrer nofollow"><span>breaks down the fix</span></a> that makes your agents&#39; output actually make sense (5.5K bookmarks). </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Reliable Harness:</b> Smart models only get you so far. This guide reveals the <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.AtRzLqL3EQmRcf6rV4XqukC77d05ic72Taj_4k1PzDkdDI2-NLzAP033Dtj1HGB6hxMbpH3EOdGzBDiAGmZgulfGFiVM3D-kpTdQNVkvrMgLXABN-Nfy6aeQZL0m7pRt8HLluhmlZ0pSDhKqcSMPvDSvi49QOlEf8B0jB9zdHOd4Z74iTrP5JVawt454Ah77sI8NcEiC_TZT-MnGdm83sNFJzbsP8iE9W0x8gtT7nP2kUfOQ8OzOEAmDOVLvFmjLcHlW6TgbjRdIZfDu2oErVOn7XgbfZ5ZNvsQBZlWVTsX4AtfU7ZSvrd-EKSPBZyRX/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h27/h001.P7mNu7nX0-8HPYpCYKXeFPVjEC-dxMcrPAj0p_G6EnE" target="_blank" rel="noopener noreferrer nofollow"><span>harness engineering</span></a> hacks you need to keep your AI agents running smoothly during long-running tasks.  </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Agent Fleets:</b> Shopify’s CEO turned his screen into a Hollywood-style hacker terminal. But the <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcFuHCNcQ_rXXuSh8ZDi0brB5I0hN6WG56gS-tYcxCW89bJO4rDYDSwZilJgvahyScCkxlv5VI8XljSRyBb3WpjsaRXETMdaLc7ctXaDc8nSi3CYiHNV-R5XdVLvrkSfnDoVY9dnHNGyrLOeXJtXfpd9IFYW8v3YyPEgZGBC1x_VDDSmDW3yBCQ4abpePirWOAvp4NFyTo0yvU0UCZdWZNtKypTEjrUKmikHnJ3EfiRcUA5AdA5mAaZ9sW1GIqmLRZg/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h28/h001.sfTBREQlBEqDoMWiNWY1CEvN1qhmP6-82roH-vraG1k" target="_blank" rel="noopener noreferrer nofollow"><span>open-source tool </span></a>behind it is the real story, and it could change the way you run your AI coding agents (3.2K likes). </p></li></ul></div></td></tr></table></td></tr><tr><td height="10.0px" style="line-height:1px;font-size:1px;height:10.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#3593ff;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>TOP & TRENDING RESOURCES</b></span></h5></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"></p></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 0.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><a href="https://link.mail.beehiiv.com/ss/c/u001.AtRzLqL3EQmRcf6rV4XqurfUThgThGIbYFq2GU1iJjwQxsNXU0JqyVaSPxRDbliM68DfLD_h3Nfq-KLxzntCpyE4rr7-Bw0dPaAcq6IeW3rqm--7ZJurNXN-INfM_hIKRS2R5n1na-YvZPdHcTB8nqZSSwG8LRCiuxJkBMy8eOKa1gCEMBETOOlNWh_PmHJBA9s6grXTJ8I5PE1ZvAe0PvbB9P3qMPJRmMs7NkeThHXWSqWVl9bAm5dFeQt7ouS3y-lsPljerXwvb3sq1p1-QXlnfV-SDoInxXRLQ0hreig/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h29/h001.VTIWISTeumA7tySY0bJ8a9JU9hQZC3Qd3Qu44zqw-xE" rel="noopener noreferrer nofollow" style="text-decoration:none;" target="_blank"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/5a13a1cf-7817-4e86-aff2-848f40154a9f/Thumbnail__3_.jpg?t=1786598697" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></a></td></tr><tr><td align="left" valign="top" class="t" style="width:670px; padding: 4px 4px 4px 4px;"><p>Click here to watch the tutorial.</p></td></tr></table></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:1px;border-color:#030712;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:10.0px 10.0px 10.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:125.0%;"><b>Top Tutorial</b></h3></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.AtRzLqL3EQmRcf6rV4XqurfUThgThGIbYFq2GU1iJjwQxsNXU0JqyVaSPxRDbliM68DfLD_h3Nfq-KLxzntCpyE4rr7-Bw0dPaAcq6IeW3rqm--7ZJurNXN-INfM_hIKRS2R5n1na-YvZPdHcTB8nqZSSwG8LRCiuxJkBMy8eOKa1gCEMBETOOlNWh_PmHJBA9s6grXTJ8I5PE1ZvAe0PjvaWMw4BU5A1lhZZu6UGZPvrlnuGml2NEd00CU9S-lfvGmZDvUbnSljRfMP4K3fHRwIdwVrNkPXdjvzG-fYdcE/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h30/h001.rTjNJc4FoZPygnNpNkBbhlUjymkvdW31FUn8hmTB3O8" target="_blank" rel="noopener noreferrer nofollow"><span><b>How to stop overpaying for agents by using Prompt Caching:</b></span></a> You’ll learn how to build cache-friendly agent harnesses that keep prompts reusable and slash token spend. This tutorial covers how to avoid costly cache invalidation and make long-running agent workflows significantly cheaper to run across all major providers. </p></td></tr><tr><td align="center" valign="top" style="font-size:0px;line-height:0px;padding:10px 0px 10px;" class="dd"><table class="j" role="none" width="98%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td> &nbsp; </td></tr></table></td></tr><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:125.0%;"><b>Top Tool</b></h3></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.wZN1XY49ssmkxVgHdsx1851aPyjaP92LUUN4x7M6BoVl7q7ZcSPuB2NRe2mKPhJ5gCdWA-Z35NVSjPYGxTePEX6PNJGSKINJmFQPEsETV1IksV4_W-_S2QDZfynNUeRhhwg_T8CTh1huhflcsjtcLjhOOmZd3z0m_wNpBUi2ap8LXZqYcRLFVIjkDX0MPDpupNyxHh2Dw9cKfYl50EG_3GV90KkE3E3nI7sPJcXaScHfZ2yPCHJOz4dpTXxcLvfK/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h31/h001.lzZykJHTHmA3uQzN-qBNSGbiw9jii7OSvKO9tAt7BdE" target="_blank" rel="noopener noreferrer nofollow"><span>Omg.dev:</span></a> You can now run coding agents like Claude Code or Codex locally on your machine and control them from your phone. </p></td></tr><tr><td align="center" valign="top" style="font-size:0px;line-height:0px;padding:10px 0px 10px;" class="dd"><table class="j" role="none" width="98%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td> &nbsp; </td></tr></table></td></tr><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:125.0%;"><b>Trending Cookbook</b></h3></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcFvzdw2aU2FVFTsci_sXq27wfceUBYlG0P14YFh-nbQFJIZTSYbAZDXG3EJPkFldJf2YZlDzQqA4liq5nH3q83r9cMiLL4BSOVU5wZj3MvauL3bDV6w1jL-EmwdJ5sbG1MZwkhZpTOOAztoufyjSRLuvu6ZWvkFUKCECuceiprdhLLv4lJQpr4Kofu_L0FMhzmOphXIpQZCsOS48VUR_yOLFXAcaG4CERRKs-UJmTrm5veTn4HFqmxMfZ75awxucyI/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h32/h001.BTWjN2tdj5WIPMgUEtyJfDXbSQpSkgj5RaZxj1uxV1Q" target="_blank" rel="noopener noreferrer nofollow"><span><b>Field guide on Grok 4.6 (by a Cursor engineer):</b></span></a> AI models often struggle with complex tasks when they rely on long prompts or assume the work is done without checking the results. This guide solves that by using concise Grok 4.6 prompts paired with strict verification steps, ensuring the AI actively tests and fixes its own output. </p></td></tr></table></td></tr><tr><td height="10.0px" style="line-height:1px;font-size:1px;height:10.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#3593ff;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>AI CODING HACK</b></span></h5></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:1px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:10.0px 10.0px 10.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h2 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:150.0%;"><b>How to stop Claude Code degrading mid-session</b></h2></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Claude Code performance tends to dip during long sessions. If you try a full refactor in one go, the second half usually ends up much sloppier than the first. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> To fix this, a senior engineer shared a sizing rule using his <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.NH9KF4GoWlrG6bVA-B2EJc5HI2THLgeYmsOoM5E0hcFCSebbUUhkG9VIfmxp_lHK8w7cspZFaeVpfmiDkUWyYf9DDhLGvQW7xDltn_J2_SRTXqsnkmjFQyhN-L6AzhY_xTHuGIuTWwbcdr80w-mYn-uQwgopX3pyoqYpOEkTNqVgi7IolOiELksPCONxiDCdTI4rYCerYHWLGsfrYaXNQglE3bdRuMw36Gh31K7GOWLJ1v-ve-EdVoV5hepPA9wzaaXjHr57BWoWLhPKsnFZYihuHnB6LCzhYyw2QNM8GOI/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h33/h001.kRZJcP1z0X7KqEEdV55xjjjNCU-BPkxjGmOvOVrIhLo" target="_blank" rel="noopener noreferrer nofollow"><span><b>/to-tickets</b></span></a> command. It breaks a large spec into smaller tickets that each fit perfectly within a single session.  </p></td></tr><tr><td style="padding-bottom:6px;padding-left:0px;padding-right:0px;padding-top:0px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ul style="font-weight:400;list-style-type:disc;margin-bottom:0px !important;margin-top:0px !important;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Step 1:</b> Install his skills plugin. </p></li></ul></div></td></tr><tr><td style="padding:0px 0px;"><pre style="background:#282828;border-radius:10px;color:#FFFFFF;line-height:1.5;overflow-wrap:break-word;padding:16px;white-space:pre-wrap;word-break:break-word;"><code>/plugin install mattpocock-skills</code></pre></td></tr><tr><td style="padding-bottom:6px;padding-left:0px;padding-right:0px;padding-top:0px;" class="ee"><div style="margin-left:0px;" class="edm_outlooklist"><ul style="font-weight:400;list-style-type:disc;margin-bottom:0px !important;margin-top:0px !important;padding:0px 0px 0px 0px;"><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Step 2:</b> Run “/setup-matt-pocock-skills” once per repo and pick a tracker: GitHub, Linear, or local markdown files. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Step 3:</b> Estimate the total tokens the task needs. It&#39;s better to overestimate. Divide that by 150K, the range where he says agents stay sharp, and round up. For example, a 1M token refactor would require 7 tickets. </p></li><li class="listItem ultext"><p style="mso-line-height-alt:150.0%;padding:0px;text-align:left;word-break:break-word;"><b>Step 4:</b> Run “/to-tickets” on your spec, check the count roughly matches your math, and implement one ticket per fresh session. </p></li></ul></div></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> P.S. Get 50+ AI coding hacks for Claude Code, Cursor, and Codex <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.nWZojHskIfWq5w8Zm9qW7smScni7E9ePvR5sqx4-vEhrh5sne6QCT0Gd4jR5noE-KnDcX2VEX6-H6mXwrLdqL6Pg7PR7i8k299H-_Dbk8evJGgOTFpO078C8TtC_32RH_TpXpEKYhDp38F_idks9VEXtIIT8ARWY7yb3S_FY5a3CpL_YUx3wPbES85Aonll1e5ADqdgVqixwvVYi0OmII-oIZualv5klEhI31L548OCh4VC55kPnyYFyEVlD8Ao21RHaliYxxAC1S1s1WJhX_g/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h34/h001.BNww15PC6jRWR379UOmQW78GF-jfXG4nwwvg1jmPbR0" target="_blank" rel="noopener noreferrer nofollow"><span>here</span></a>. </p></td></tr></table></td></tr><tr><td height="10.0px" style="line-height:1px;font-size:1px;height:10.0px;"> &nbsp; </td></tr></table></td></tr><tr><td align="center" valign="top" style="padding-bottom:0px;padding-left:0px;padding-right:0px;padding-top:0px; " class="dd"><table role="none" border="0" cellspacing="0" cellpadding="0" style="margin:0 auto 0 auto;"><tr><td align="center" valign="top" style="width:670px;"><img src="https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80,width=1920,height=3840/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539" alt="" height="auto" width="670" style="display:block;width:100%;" border="0"/></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:0px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:0.0px 0.0px 0.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h5 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:100.0%;"><span style="color:#3593ff;font-family:Eczar,Lora,'DejaVu Serif',Georgia,serif;"><b>IN CASE YOU MISSED IT</b></span></h5></td></tr></table></td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:1px;border-color:#030712;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:0px;padding:10.0px 10.0px 10.0px 10.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" valign="top" style="color:#2A2A2A;font-weight:400;padding:0px 0px;text-align:left;"><h3 style="color:#2A2A2A;font-weight:400;mso-line-height-alt:125.0%;"><span style="background-color:#ffffff;"><span style="font-family:inherit;font-size:18px;font-weight:600;"><b>Our most-clicked story from yesterday</b></span></span></h3></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Check out this <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.yBywWjiZ7oCsTrXLmaNhku5e8NxXVaslx9OG2lhnNha9TjzVwKzRvqlL3jeqb67LJejhdJBVQUQ82Z__zitMY_TWuhssc9Zm86XSkP5BgwBlsT17aGCt7JAnGmMRVcXAWrbZcj-2LrErzW5gdApQQec5FrA1HJCxVYGc1ILb8k_xNQFadtRVCMco95w42_0LIBVQftsqUZJ8XWf-aKq0YI_ktNv-g43O6Evb4vHVIHh919t_TR-5dihNlii1iKAIOqN6zCmNLzJ30HmEwek9cI-cY0unuGsUYZUmrlH-BoQ/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h35/h001.orwhqP91Sehdpzwlt65vgFGPbVzCDlFJkYGrKjcKsoY" target="_blank" rel="noopener noreferrer nofollow"><span><b>GitHub repo</b></span></a> to remove Claude’s watermarks from your content. </p></td></tr></table></td></tr><tr><td height="10.0px" style="line-height:1px;font-size:1px;height:10.0px;"> &nbsp; </td></tr></table></td></tr><tr><td><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" style=""><tr><td bgcolor="transparent" style="background-color:transparent;border-bottom-width:1px;border-color:#222222;border-left-width:1px;border-right-width:1px;border-style:solid;border-top-width:5px;padding:8.0px 8.0px 8.0px 8.0px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0"><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"><span style="background-color:#f1ff00;"><b>Grow customers & revenue:</b></span> Join companies like Google, IBM, and Datadog. Showcase your product to our 300K+ engineers and 150K+ followers on socials. <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.AtRzLqL3EQmRcf6rV4Xqukg2WkDQFtGSBHA5_1_aSjBSny57Pg9S0g8rkJc0Vn9fVlKpmUYIKtbzCNK49A4bb2FGoMHQ-Kl1xF4r_ygjggEXBnwdJX50VI3VNf5mA585owMzx2EeI3dszJEDUwWbnt7zEQ7M5QjXl1BwDGap1Gdlh-mYaf70-vYdoCO78ZZY9g3otnKC9uuo3KlbAd5EwFtFDFjqqVao3w2Rs2M5GmmuOz-GiH4h5cNeyuP_QPxr5KvyQHK0h1DWBs9WHW-tgQ/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h36/h001.kMvbQVl9XnXF5Df9TIGFJu8MQqdn6ykZRnDkupAhdd4" target="_blank" rel="noopener noreferrer nofollow"><span>Get in touch.</span></a></p></td></tr><tr><td align="center" valign="top" style="font-size:0px;line-height:0px;padding:10px 0px 10px;" class="dd"><table class="j" role="none" width="98%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td> &nbsp; </td></tr></table></td></tr><tr><td class="e" align="left" valign="top" style="padding:0px 0px 7px;"><h3 style="">What did you think of today&#39;s newsletter?</h3><p style="">Your feedback helps us create better emails for you!</p></td></tr><tr><td class="ee e " style="padding:0px 0px 0px;"><div style="margin-left:0px;" class="edm_outlooklist"><table role="none" border="0" cellspacing="4" cellpadding="0" align="left" style="min-width:300px;"><tr><td style="width:100%;border:1px solid rgba(50, 50, 50, 0.17);padding:6px 12px; border-radius:4px;"><a style="font-style:normal;text-decoration:none;" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9su7eJ8jn4pJH4nJy1BDM8Ka3gPzzyaeb0Zt71C26KnZc8na-mYFOCr9-W0iXrbrAM58ub9i1cevY3jG7xK5UcPDwnz6tsGkkjTmiKFcuJ05ZmBHGZ0D0BLYe7bZbQP6GFjZZtFZnnBdy7qjPO5bbscU6oFz11btD8jG_ZuFEeCCCy7V44TWLUEoWD2TjTqyvXqrbd_Vc2dvTLuv5MtbYFX5xu7s4VAyxB3i2EQHusjRosfe5gTFrtLAvqQ_cVZDoEcXnMysrIzq5q7pFIEh4Fnj07JFLdBhtnrNWk2-dILRmBptylAhL-r3yVPIrhFs72RKYaEb_LsMfc6mZuLfIp2pjKYvkJ3KexWofrEnvKnzSlVr_2cgNwUlK9WeuOyIYtwC43rCGcKG5gmdalLpfwpYnqlmOlD5Syd9vZ3X4QkizSfQfAk3d9mJ9LRyJyiYsDuXR6GEI8szSauBvFERavM51_b01QV3LWsy--v2D7c4dbWJP_8wRiqEToTRem5w4sdQM_ZGcZGkoDhmTX2699lP5W1Ix25zhtZFMDaRmhWoQtkofndsOR7lRCHbYG4WM05MK8vAeXmEGo_OinKbvhsS7Yo8eW6qvXrVqNhKUjbd6EvsCx8P7wJwHLznMnRuAy3vHZPtDUVVvlUwax7Gr4892LIDhf4fnw0_DOD5gz4czqIORYSGTffb0rJHnZNbNphYFeyp4mAq7EwaPnW3oXTz1nBlmYEN0U3GPcMdlyQD9cPvoiKc1-THagY46jJITUpkYNwpPS1oxI3NtKSoT2Fug7gNmT4S87AQ4Auf6_F_lDFPWBsiGhChJuz13lGGZd5QUBEQu2RzQcrZc1fk1djMDfKtygTFU6Vnd9CEIfnE_4cO_Rvk312itpyNlIOKatmoN_Zzqlfl7EcNwmH3eFeJhm-LmvwGF93YDxL-6SlsGIiZCo4lV6AOUDTYk9q3WhetXnG7o2G3N8SZjAGZaPjdH9Xn8VSqVVz5EDzS7_6BBQ-WilUOmpO_0hPtfBmfog/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h37/h001.Vplr9ZLByUE2ItweohtmLZA1he_8RiBIhh33z04DVWA"><p style="font-size:14px;color:inherit;"> Loved it 🧠🧠🧠 </p></a></td></tr><tr><td style="width:100%;border:1px solid rgba(50, 50, 50, 0.17);padding:6px 12px; border-radius:4px;"><a style="font-style:normal;text-decoration:none;" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9su7eJ8jn4pJH4nJy1BDM8Ka3gPzzyaeb0Zt71C26KnZc8na-mYFOCr9-W0iXrbrAO_5iK01-grb5B6b9rxJbggCgMjlnTyujZ67LuZkL4w3QYbSZASQEjt_h9ck9FHbNLiaLNAYBtTA639_PIoUSm6BBxXI4y8CoPtXWv6qlxEyav-W2c8i-jv9qoQZGJ6-EO9jXC-npnsYjNS3XVgWeofEdaXjh9GeEoljAXNLAVppp2ohXJrNaD79PY0ygcaZmuHQMK-rYM4YauXwBqrH4Lp66cGe1UmMI3FS6__0TQo6jq1QJZAI_5xuxj99SOnpKBJuMJ_x8fZYjLzporPGMGJrq7Bz4b-E8YvxiwT-FX69CycZ4s3Qit3V0n1UUvNgT0xaL0AK11sWu5J-_L2FwtbssvF3sU2oEI4L7TpTPcl1kdS2E5ol_En-UNaEADiBOyEhgXq61d2ZWQp3LQQWM79uqY1A7Hmsj94iR7Q8UvY15TLCtswgPgk7CFkj_QatGaWbRnJ8eXmkMTZgyD9LNYCykVAMCRZ2-lUnVRT07I_ubK2SFs-BWxIOXmRdEGrXrwi4RLOrhiXzK2rv0Rx5y3MedzsLPNBNLi8ReILDA4KCltZHd6JCwjHDXmmF3wFvwBTlg1qzdDPGgAhLF4Z_n9IMAvOhaZyzQmGMVtcVxtdPP1RDRyLu41qWuD0kZb8jbakyBJSHu0KW7cyH8uJFG9mLzlnHZApFjqE5kBaX0xLs_X1pfO8M_zL4UX-RmYAUt0pwq_ZsjMMMkBgVxOQFDGgGAMb4psM4G6zS9OS5AmeWGaHla1VJKf_UguvOwRbgZt2OntqWz_xZFOD8hW9M18N_qOOWvHbgXKofhElLfGwVHeeEeCENlqDjH4dCBbrVSQ_KVpgKMPt-rzuH4uFKCFgkZjYaZqHc0EdewbSATsJAD8Ar7XFL-lWfzfNyh_PG5yL8jLcWhgnWPCyzYtNY0FyDjUfJhuvt53z02_lMdPI93pPWK_iQnQLGIYL7SrIbtc/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h38/h001.dupODVeK_itlWQFS-j6pTx-LAxQoz-nkOSVkERkhfTQ"><p style="font-size:14px;color:inherit;"> Average 🧠🧠 </p></a></td></tr><tr><td style="width:100%;border:1px solid rgba(50, 50, 50, 0.17);padding:6px 12px; border-radius:4px;"><a style="font-style:normal;text-decoration:none;" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9su7eJ8jn4pJH4nJy1BDM8Ka3gPzzyaeb0Zt71C26KnZc8na-mYFOCr9-W0iXrbrANqaaF2ft4LZNSaoIDXjUpqdWD4X47Cztewvx9_eSAMyt-U_s6AftXBC3OfCry1RhCK9AsOdgju9eBo89L0sOld8XUmvackcHa6pwuyoXp8idC29aBHHdlEYbYIh6OAD2iGfsnKstZZf9FrT8ZqOo49U-mO4Xwz82Ai7sAp40V_pcrPbIJ1LilVSyh3Y0n29zCU3aulUDER2_ZaDMGEZKIA-e0t_zP4nu4et5Ne1Y9_facP8kxqn_KZaSDhIAO7qz7l9QOl4OpANb8jkbAIYMqtOp7erZQGH_-EFKxEUhg9VpkZn2_R6rjtyGRKfhgBY60YVIF1UCc85fNJr3SP9L25O8_bZUdxyrLsAfNsNJwHOETKqcZMMzemLB735WeKaTLOia1AY9cLJDtuGshd2K6mE2GLamjNbLMDmCM5kmzBVYqnXS_VEMbfs-wvHSDNAWCZr7CD-pkhPPVwdRass24-HIKT53gANw80Nr9TBgDW8eq38o-jiIi7fCDDsJLVwGgY9-uiZKurnLclUmPF5M5yEI3rKce2aZwnqiMW9FttOwvwwwjjkq6Vjdu_niiJ64Wd0DwZN8lZigDH1y7sv7lhTcO4J7ApkLfcyDb1-v6vPNwRA32h0uLR2cRPWCXMHYUqSVvMNCO_WSJN5qxC1AQF_y4iQKCWGnskMs8t6Jqi-HqTJsXc8D5ivJjQjvR5nXy2Y1B6RHlOIU9IleTP0fAJGTj5AGC2zMwPK9IrdjoY2NkCw09dKfioDsF2ANj8JGh-QXhFEwLm_w6Ymy8GyYACBWWTLDF0t02pzBuhNXQ5RBVVw3BrvM_paGCWU3Ec4iLBdjIBQksVMrfpd1NXvYeRU-mXcaWQIvwPjfqNKEtyba90zU46jy7XTw_ZCKTiOlJ9e6HrmwZQYuJ2Tq7um6VsN54nZujyk3S7qSS_KgYyTErvHg2XNk7Qrd3mEM3HWUU/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h39/h001._jzxR_3X5Tr_d9CaaqfK62K1ilrgDwFyywGJ8V9WXEU"><p style="font-size:14px;color:inherit;"> It sucked 🧠 </p></a></td></tr></table></div></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> You can also reply directly to this email if you have suggestions, feedback, or questions. </p></td></tr><tr><td class="dd" align="left" style="padding:0px 0px;text-align:left;word-break:break-word;"><p style="mso-line-height-alt:150.0%;"> Until next time — The Code team </p></td></tr></table></td></tr><tr><td height="10.0px" style="line-height:1px;font-size:1px;height:10.0px;"> &nbsp; </td></tr></table></td></tr></table></td></tr></table></td></tr><tr><td align="center" valign="top"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td><tr><td class="b" align="center" valign="top" bgcolor="#030712" style="padding:0px 0px 0px 0px;border-style:solid;border-width: 0px 0px 0px 0px;border-color: #FFFFFF;border-bottom-left-radius:10px;border-bottom-right-radius:10px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td height="10" style="line-height:1px;font-size:1px;height:10px;"> &nbsp; </td></tr><tr><td class="w" align="center" valign="top" style="padding:15px 15px 15px 15px;"><table role="none" width="100%" border="0" cellspacing="0" cellpadding="0" align="center"><tr><td align="center" valign="top"><p style="font-family:'Verdana',Geneva,sans-serif;color:#FFFFFF!important;"> Update your email preferences or unsubscribe <a class="link" href="https://link.mail.beehiiv.com/ss/c/u001.kro7WBsAmEsY5mGgiUDePbOdMF_BvViPt7FxYKgxL9szpjhO_X7CGaQ-dHuFN4dv2nDJM7VwywhH_aNIWJ7DpCUiK5m3JnN9be-e_wBbmchHe5y58AGenpvwTn14-nulyC-_JwpUVM7KA0OnXpVJ8PDheBncTvxJ39Gc50EYvnY889EEi6zsara-cIfNrexpfHCoc1DI6qFwMbtEnuK0Iaydgwoh4PdG2P7SnDCuUxAF8BFkM6_aq1Gzxh9JIPcAXWODkTfGRxMYu_ND7JXCFmadUoRpvjc3Il0__2625HUngVST2URro_7JYgSViTVoOt9hC0P8_rr9G6zSCLG-cPsbrRIo_kuOWawxyShoRTrds9Qw_CXtyBPX06JazvAh3DCTth6V7jGcwbCUtDPl22DJ234q_xbScwePSFMcpTrbIw7Dg1p0o-VctEYs9s2G3NDsdFyTc99BVi3ur2-AJVP1WLPCe_7MYPAnHJnSLfkxli8Ofa2uDK36rdbA2s72RifiTWxGTDdqhP2epWp65uX5S1IvHxZNs8gIUmgVC9DoJguyWFnPDoFUJyP1zQpSuG3ot5dPQA9Y_XH7W1eT6DWb6uErgrKj_fJ7MONg0pdkUvSB7YqLI_W_UK0Y7J58yvGgClb6ubjCA6dDn-IU7nUk1MVALqyXNRRFiACY_3DvUHYn2SQgwv48W-Czd2_oYLJPXpmPFhCIn2hkcYVm6650S8-ySeqppAZXhfn-WCqL-EHLDXh3c_VP8IoXsLzN3tufPkK3kZDvww2hD5HRPXdrXP_rfHlRK8-fm_WWBCDX6nQO28fxn1OF514zljHPNOZz--pe4EPRZxKYTHgX1gAE8pFK3LkHYkpKNjf7LGUfHc7A7kq6N6xX9G6u1nBQGWdGhDaq2reH-Atjll5IvPVGmTtelhNTOGAgh1mpvm311Y2MSGjNF4VtHrtoXRR6LM9fXY1cWk-DyjN9dYu9aWGLsB5ynge7F1l3aoeS9X63mcAPoSWNWXzSnLJA7aQH2EKjFxbHKMJIjnqi7sjGJpGiOlG0QnnkWbQUv16Epwo/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h40/h001.Ix3Dh_kMdGlV0ALk_n0NbqOo59lGgoqXptQWfO1rF2U" style="text-decoration:underline;text-decoration-color:#FFFFFF!important;color:#FFFFFF!important;"> here</a></p><p class="copyright" style="font-family:'Verdana',Geneva,sans-serif;color:#FFFFFF!important;"> &copy; 2026 The Code </p><p style="font-family:'Verdana',Geneva,sans-serif;color:#FFFFFF!important;"> 228 Park Ave S, #29976, New York, New York 10003, United States </p></td></tr><tr><td align="left" valign="top" height="2" style="height:2px;line-height:1px;font-size:1px;mso-line-height-rule:exactly;"><a href='https://link.mail.beehiiv.com/ss/c/u001.nWZojHskIfWq5w8Zm9qW7uhFPeDiAXllchtVb3ARdSmgeTOVYjNABTLSj0sIlkKCskkGgA1RO9I5oiggfHFCsCKEetsAfCqK7dGXR0zIuNc/4t5/vwXXKwJ4RBa8bnAdGR1jJw/h41/h001.psEC4R7l6o4AL48BFj5Y8o-pvu5kpG1d_CJze3KVQSY' style="color: #030712 !important; cursor: default; font-size: 1px; text-decoration: none;"></a></td></tr><tr><td align="left" valign="top" height="2" style="height:2px;"><a href='https://email.beehiivstatus.com/dd7f87df37032ed6171da82445fedd67a8c67852/hclick' clicktracking="off" style="color: #030712 !important; cursor: default; font-size: 1px; text-decoration: none;"></a></td></tr></table></td></tr></table></td></tr></td></tr></table></td></tr></table></td></tr></table></td></tr></table></div></body></html>
                                

Plain Text

                                    View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/608575f2-530e-4b3f-a60c-016474dac011/Group_Agentfield__6_.png?t=1786586886)
Follow image link: (https://agentfield.ai/github/pr-af/?utm_source=thecode&utm_medium=newsletter&utm_campaign=thecode-260813&utm_id=thecode-260813-pr-af&utm_content=pr-af)
Caption: 

----------
**Welcome back.** ==Last year, a group led by OpenAI researchers dropped "AI 2027," a roadmap predicting what AI would look like over the next two years. Fast forward to today, and ==19 of the 53 tracked predictions are confirmed or ahead of schedule==. Check out ====[the full timeline](https://archive.codenewsletter.ai/2087452378299564147)==== to see what’s changed.==

==**Also:**==== A detailed guide on harness engineering, fixing your home wifi with Codex,== and how to humanize AI PRs of your dev team.


--------------------
### **Today’s Brief**

* How Databricks manages AI coding costs

* How Apple could win the AI race

* Save token costs by prompt caching (tutorial)

* Field guide on Grok 4.6 (cookbook)


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **TODAY IN PROGRAMMING**




--------------------
View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/215702da-08df-4444-a965-d504b6de4300/Thumbnail__6_.jpg?t=1786623024)
Follow image link: (https://x.ai/news/grok-4-6)
Caption: Click here to check out the specs.


--------------------
**SpaceXAI’s new model targets long-running agents and large codebases:** Elon Musk's AI lab just unveiled [**Grok 4.6**](https://x.ai/news/grok-4-6), a model specifically designed to handle multi-step workflows. Whether it researches a codebase, structures an app, or iterates based on feedback, this model performs reliably over the long haul. It’s currently available via Cursor, Grok Build, and the API at a rate of $2 per 1M input tokens. Devs are already giving this model a shot. Shopify CEO’s [post](https://archive.codenewsletter.ai/2087704273438052632) about the model's animated reaction during a maintenance task is making rounds on the internet.  

**Alibaba open-sources its most powerful model to date:** The Chinese tech giant just dropped a new version of [Qwen3.8](https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B-FP8) on Hugging Face. The company claims the model goes head to head with the top frontier models on coding and agentic benchmarks. But there is a catch for devs: you will need a massive 4.9TB of storage to run it at full precision. Even with [Unsloth’s 1-bit build](https://unsloth.ai/docs/models/qwen3.8) (which trims that down to 397GB), you are still going to need some serious RAM. If you want to run this locally, a lighter 27B version will drop soon. [More details here.](https://modelscope.ai/models/Qwen/Qwen3.8-2.4T-A95B)

**DeepSeek's flagship nears frontier coding at a fraction of the cost:** The Chinese AI startup just moved [V4 Pro](https://archive.codenewsletter.ai/2087602193205694891) from preview to general availability while maintaining its current pricing. It costs $0.435 per million input tokens and $0.87 per million output tokens, which represents a small fraction of the Fable 5 rate. The model supports a 1M token context window and tool calling, allowing it to integrate seamlessly into your agent pipelines. While it still trails slightly behind Fable 5 in agentic coding performance, these results come from the company's own unverified benchmarks.  


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **PRESENTED BY AGENTFIELD**

## [Open source hit frontier-level code review at a tenth of the cost.](https://agentfield.ai/github/pr-af/?utm_source=thecode&utm_medium=newsletter&utm_campaign=thecode-260813&utm_id=thecode-260813-pr-af&utm_content=pr-af)


--------------------
View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/a8bd2252-3c0b-4d2a-8b3d-238db94e04c3/thecode-pr-af-podyum-1920x1080-100k.jpg?t=1786586957)
Follow image link: (https://agentfield.ai/github/pr-af/?utm_source=thecode&utm_medium=newsletter&utm_campaign=thecode-260813&utm_id=thecode-260813-pr-af&utm_content=pr-af)
Caption: 


--------------------
An open-source reviewer now places #2 of 42 on Martian's Code-Review-Bench, ahead of the commercial tools, at ~10x lower cost per review. 

[PR-AF](https://agentfield.ai/github/pr-af/?utm_source=thecode&utm_medium=newsletter&utm_campaign=thecode-260813&utm_id=thecode-260813-pr-af&utm_content=pr-af) plans the review per PR, runs reviewer agents in parallel, and verifies every finding against your source before it posts, so no hallucinated comments. 0.706 recall, roughly 3x more valid findings. Apache 2.0, self-hosted, runs on any open or closed model.

[**Star & Deploy**](https://agentfield.ai/github/pr-af/?utm_source=thecode&utm_medium=newsletter&utm_campaign=thecode-260813&utm_id=thecode-260813-pr-af&utm_content=pr-af)


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **INSIGHT**




--------------------
## **So your AI coding costs keep climbing, but you cannot contain it. Here’s how Databricks manages it:**


--------------------
View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/9167cc65-65ec-4d42-b4f9-293065318fd8/Thumbnail__4_.jpg?t=1786612863)
Caption: Source: Databricks


--------------------
**The wall everyone hits.** Agentic coding can help your engineering team ship up to 10x faster, but the costs can spiral even quicker. If you aren't careful, your AI bill will eventually outweigh the actual value it delivers. Databricks calls this a solvable engineering problem. According to their internal playbook, teams that successfully manage these costs lean on four main strategies, ranked here by impact:  

* **Lean on lower-cost models.** Start with the cheapest model that clears your quality bar, including open-source options like GLM. Most everyday coding doesn't need the most powerful model available. This can cut costs by 50% or more.

* **Route work automatically.** Developers shouldn't have to pick a model for every task. A smart router can send each job to the cheapest model capable of handling it.

* **Swap caps for friction.** Hard budget restrictions should be a last resort because they can punish the engineers getting the most value from these tools. Instead, show spending in real time, add warnings for usage spikes, and quietly shift work to cheaper models when necessary.

* **Trim the context.** Even the cheapest models get pricey when you're feeding them too much data. Honestly, most of that context is being added by your coding harness, not the developer. If you tune your harness and cache settings, you can pretty much cut your generated tokens in half without seeing any drop in quality.  

**The starting point.** Combine these levers, and unit costs can fall by as much as 90% without a quality hit. But you should start small. First, look at your team's spending, identify the models and tools driving the bill, and then tackle the biggest source first. 

P.S. Databricks' full [walkthrough](https://www.databricks.com/blog/managing-ai-coding-costs-scale) covers the tooling, while its open-source Omnigent [meta-harness](https://docs.databricks.com/aws/en/omnigent/) lets teams experiment with model switching themselves.


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **OPINION**


--------------------

----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **PRESENTED BY SONIOX**

## [Give your product a voice worth listening to](https://soniox.com/text-to-speech?utm_source=the-code)


--------------------
View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/b0daeeed-b488-47f6-8a4b-8142a3a5d3f7/The_Code_Feature_Ad__5___1__-_Slava_Obukhov.jpg?t=1786538400)
Follow image link: (https://soniox.com/text-to-speech?utm_source=the-code)
Caption: 


--------------------
[Soniox Text-to-Speech](https://soniox.com/text-to-speech?utm_source=the-code) lets you create extraordinary voice experiences in 60+ languages with expressive control, exceptional precision, instant voice cloning, and ultra-low-latency streaming.

Direct whispers, laughter, hesitation, excitement, and emotion, or precisely speak phone numbers, email addresses, technical terminology, and multilingual text.

Built for voice agents, global products, customer support, media, and any application where speech needs to sound human and get every detail right.

$0.70 per generated hour.

[**Try it now**](https://soniox.com/text-to-speech?utm_source=the-code)


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **IN THE KNOW**

## **What’s trending on socials and headlines**


--------------------
View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/25632e7b-6e42-4d5e-9ba0-8d0fb9757857/CleanShot_2026-08-13_at_15.52.53_2x.jpg?t=1786616612)
Caption: Meme of the day.


--------------------
* **WiFi Fix:** A tech CEO pointed ChatGPT Work and Codex at his patchy home WiFi and let them troubleshoot the whole thing. Here's the [prompt he ran](https://archive.codenewsletter.ai/2087299373848002706) (3.4K bookmarks).

* **Apple's Play:** While US companies burn cash racing Chinese AI labs, this viral theory explains how [Apple could win the AI race](https://archive.codenewsletter.ai/2086901687365837171) without ever building a model (574K views).

* **Fix AI slop: **Ever noticed how AI-written PRs look polished but are actually a total mess? This post [breaks down the fix](https://archive.codenewsletter.ai/2087294922378637680) that makes your agents' output actually make sense (5.5K bookmarks).

* **Reliable Harness:** Smart models only get you so far. This guide reveals the [harness engineering](https://walkinglabs.github.io/learn-harness-engineering/en/) hacks you need to keep your AI agents running smoothly during long-running tasks.  

* **Agent Fleets:** Shopify’s CEO turned his screen into a Hollywood-style hacker terminal. But the [open-source tool ](https://archive.codenewsletter.ai/2086488457132626052)behind it is the real story, and it could change the way you run your AI coding agents (3.2K likes).


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **TOP & TRENDING RESOURCES**




--------------------
View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/5a13a1cf-7817-4e86-aff2-848f40154a9f/Thumbnail__3_.jpg?t=1786598697)
Follow image link: (https://www.youtube.com/watch?v=SkM4k4SKvCM)
Caption: Click here to watch the tutorial.


--------------------
### **Top Tutorial**

[**How to stop overpaying for agents by using Prompt Caching:**](https://www.youtube.com/watch?v=SkM4k4SKvCM) You’ll learn how to build cache-friendly agent harnesses that keep prompts reusable and slash token spend. This tutorial covers how to avoid costly cache invalidation and make long-running agent workflows significantly cheaper to run across all major providers.

———————————————————————————

### **Top Tool**

[Omg.dev:](https://omg.dev/) You can now run coding agents like Claude Code or Codex locally on your machine and control them from your phone.

———————————————————————————

### **Trending Cookbook**

[**Field guide on Grok 4.6 (by a Cursor engineer):**](https://archive.codenewsletter.ai/2087566447178547494) AI models often struggle with complex tasks when they rely on long prompts or assume the work is done without checking the results. This guide solves that by using concise Grok 4.6 prompts paired with strict verification steps, ensuring the AI actively tests and fixes its own output.


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **AI CODING HACK**


--------------------
## **How to stop Claude Code degrading mid-session**

Claude Code performance tends to dip during long sessions. If you try a full refactor in one go, the second half usually ends up much sloppier than the first. 

To fix this, a senior engineer shared a sizing rule using his [**/to-tickets**](https://archive.codenewsletter.ai/2087111966854730148) command. It breaks a large spec into smaller tickets that each fit perfectly within a single session.  

* **Step 1:** Install his skills plugin.

```
/plugin install mattpocock-skills
```
* **Step 2:** Run “/setup-matt-pocock-skills” once per repo and pick a tracker: GitHub, Linear, or local markdown files.

* **Step 3:** Estimate the total tokens the task needs. It's better to overestimate. Divide that by 150K, the range where he says agents stay sharp, and round up. For example, a 1M token refactor would require 7 tickets.

* **Step 4:** Run “/to-tickets” on your spec, check the count roughly matches your math, and implement one ticket per fresh session.

P.S. Get 50+ AI coding hacks for Claude Code, Cursor, and Codex [here](https://hackbook-chi.vercel.app/).


----------View image: (https://media.beehiiv.com/cdn-cgi/image/fit=scale-down,format=auto,onerror=redirect,quality=80/uploads/asset/file/18efc0eb-c3c4-483f-a001-0fe0dcca16c3/Group_from_Figma__2_.png?t=1758120539)
Caption: 

----------
##### **IN CASE YOU MISSED IT**


--------------------
### ==**Our most-clicked story from yesterday**==

Check out this [**GitHub repo**](https://github.com/guillaumemeyer/watermarks-remover) to remove Claude’s watermarks from your content.


--------------------
==**Grow customers & revenue:**== Join companies like Google, IBM, and Datadog. Showcase your product to our 300K+ engineers and 150K+ followers on socials. [Get in touch.](https://www.passionfroot.me/the-code)

———————————————————————————

You can also reply directly to this email if you have suggestions, feedback, or questions.

Until next time — The Code team


----------
———

You are reading a plain text version of this post. For the best experience, copy and paste this link in your browser to view the post online:
https://codenewsletter.ai/p/spacexai-s-new-model-targets-long-running-agents

                                

Warning

Almost all the messages that arrive here are garbage! Resist the urge to click on any unexpected or questionable links.

It may happen that e-mail will claim to come from liamon.com, perhaps from some administrative role or process. There are no users with liamon.com addresses that should be sending anyone e-mail. There are no accounts to expire. There are no passwords to leak. These are certainly garbage messages. These are certainly phishing attempts in some messages.

Absolutely ignore those links!