# Blog Read about our latest announcements. [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fdevin-security-2%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/devin-security-2) [Product](https://devin.ai/blog/devin-security-2) ## [Devin Security 2.0: Built for the new threat landscape](https://devin.ai/blog/devin-security-2) [Frontier-model scanning, prioritization grounded in your environment, and autonomous remediation that turns security findings into pull requests.](https://devin.ai/blog/devin-security-2) [October 26, 20268 min read](https://devin.ai/blog/devin-security-2) [All](https://devin.ai/blog)[Product](https://devin.ai/blog/category/product)[Enterprise](https://devin.ai/blog/category/enterprise)[Changelist](https://devin.ai/blog/category/changelist)[Company](https://devin.ai/blog/category/company)[Industry](https://devin.ai/blog/category/industry)[Case Studies](https://devin.ai/blog/category/case-studies) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fvulnerability-fixes-plugin%2Fsecurity-blog-2.jpg\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/vulnerability-fixes-plugin) [Product](https://devin.ai/blog/vulnerability-fixes-plugin) ## [Fixing Critical Node & PHP Flaws](https://devin.ai/blog/vulnerability-fixes-plugin) [On October 21, 2026 the PHP and Node.js projects released security updates addressing vulnerabilities that can allow remote code execution. We packaged the remediation workflow we used ourselves into Vulnerability Fixes, an open-source plugin for Devin and any coding agent: it identifies affected repositories, asks before changing anything, patches each deployment to a verified fixed version, tests before and after, and opens one focused PR per repo.](https://devin.ai/blog/vulnerability-fixes-plugin) [October 22, 202611 min read](https://devin.ai/blog/vulnerability-fixes-plugin) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fefficiency-based-cost-controls%2Fcover.jpg\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/efficiency-based-cost-controls) [Product](https://devin.ai/blog/efficiency-based-cost-controls) ## [A smarter approach to AI cost controls: allocating spend by efficiency](https://devin.ai/blog/efficiency-based-cost-controls) [Blanket usage caps hold back your most efficient engineers. Efficiency Score, Devin Coach, and efficiency-based approvals let enterprises allocate AI spend by engineering efficiency instead.](https://devin.ai/blog/efficiency-based-cost-controls) [October 19, 202610 min read](https://devin.ai/blog/efficiency-based-cost-controls) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fintroducing-devin-oncall%2Fcover.jpg\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/introducing-devin-oncall) [Product](https://devin.ai/blog/introducing-devin-oncall) ## [Introducing Devin Oncall](https://devin.ai/blog/introducing-devin-oncall) [Devin Oncall is now generally available. Devin automatically investigates alerts and bug reports and helps your team diagnose and resolve production incidents.](https://devin.ai/blog/introducing-devin-oncall) [October 15, 202610 min read](https://devin.ai/blog/introducing-devin-oncall) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fdevin-in-pylon%2Fcover.jpg\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/devin-in-pylon) [Product](https://devin.ai/blog/devin-in-pylon) ## [Devin in Pylon: Driving faster Median Time To Fix](https://devin.ai/blog/devin-in-pylon) [Support teams can now start Devin investigations directly from Pylon, and engineers pick them up with the first pass of work already done.](https://devin.ai/blog/devin-in-pylon) [October 13, 20265 min read](https://devin.ai/blog/devin-in-pylon) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fgemini-4-argon%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/gemini-4-argon) [Product](https://devin.ai/blog/gemini-4-argon) ## [Gemini 4 Argon is now available in Devin](https://devin.ai/blog/gemini-4-argon) [Gemini 4 Argon is now live in Devin Desktop and Devin CLI, at 75% off list price through October 27, 2026. On FrontierCode 1.1 it scores 60.5%, surpassing GPT-6.1 Sol and matching GPT-6 Sol, the highest score of any Gemini model on the leaderboard.](https://devin.ai/blog/gemini-4-argon) [October 13, 20261 min read](https://devin.ai/blog/gemini-4-argon) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fclaude-haiku-5-5%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/claude-haiku-5-5) [Product](https://devin.ai/blog/claude-haiku-5-5) ## [Claude Haiku 5.5 is now available in Devin](https://devin.ai/blog/claude-haiku-5-5) [Claude Haiku 5.5 is now live in Devin. On FrontierCode 1.1 it scores 58.4%, ahead of Sonnet 5 at about an eighth of the cost per task, and it joins the sidekick lineup in Devin Fusion.](https://devin.ai/blog/claude-haiku-5-5) [October 7, 20261 min read](https://devin.ai/blog/claude-haiku-5-5) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fmemory-and-dreaming%2Fcover.jpg\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/memory-and-dreaming) [Product](https://devin.ai/blog/memory-and-dreaming) ## [Memory and dreaming: how Devin learns from working with you](https://devin.ai/blog/memory-and-dreaming) [Memory lets Devin carry useful learnings about the way you like to work across sessions. Dreaming is a daily asynchronous process that improves the index of Devin's memories about you.](https://devin.ai/blog/memory-and-dreaming) [October 5, 20263 min read](https://devin.ai/blog/memory-and-dreaming) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fgpt-6-1-sol%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/gpt-6-1-sol) [Product](https://devin.ai/blog/gpt-6-1-sol) ## [GPT-6.1 Sol is now available in Devin](https://devin.ai/blog/gpt-6-1-sol) [OpenAI released GPT-6.1 Sol. It is live now in Devin Desktop and Devin CLI. Same $2/$10 list price as GPT-6 Sol, but cache reads are now 95% off, and on FrontierCode 1.1 it matches GPT-6 Sol's score at roughly half the cost per task at every reasoning effort. At low effort it scores 58.1% for $0.21 per task, the best score of any model under $0.30.](https://devin.ai/blog/gpt-6-1-sol) [September 29, 20261 min read](https://devin.ai/blog/gpt-6-1-sol) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fsign-in-with-chatgpt%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/sign-in-with-chatgpt) [Product](https://devin.ai/blog/sign-in-with-chatgpt) ## [Sign in with ChatGPT](https://devin.ai/blog/sign-in-with-chatgpt) [You can now sign in to Devin with ChatGPT and use your eligible ChatGPT Plus or Pro plan for OpenAI model usage across Devin Cloud, Devin Desktop, and Devin CLI.](https://devin.ai/blog/sign-in-with-chatgpt) [September 29, 20262 min read](https://devin.ai/blog/sign-in-with-chatgpt) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fdevin-for-mongodb-modernizations%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/devin-for-mongodb-modernizations) [Product](https://devin.ai/blog/devin-for-mongodb-modernizations) ## [Cognition and MongoDB partner to modernize enterprise infrastructure in months, not years](https://devin.ai/blog/devin-for-mongodb-modernizations) [Cognition and MongoDB are bringing Devin into MongoDB’s Application Modernization Platform (AMP) to help customers migrate legacy applications to MongoDB Atlas.](https://devin.ai/blog/devin-for-mongodb-modernizations) [September 29, 20263 min read](https://devin.ai/blog/devin-for-mongodb-modernizations) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fclaude-sonnet-5-5%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/claude-sonnet-5-5) [Product](https://devin.ai/blog/claude-sonnet-5-5) ## [Claude Sonnet 5.5 is now available in Devin](https://devin.ai/blog/claude-sonnet-5-5) [On FrontierCode 1.1, Sonnet 5.5 is a significant improvement from Sonnet 5 at 64.4%, surpassing even Fable 5.1 at extra high reasoning effort.](https://devin.ai/blog/claude-sonnet-5-5) [September 28, 20261 min read](https://devin.ai/blog/claude-sonnet-5-5) [![](https://devin.ai/_next/image?url=%2Fimages%2Fblog%2Fmore-efficient-devin%2Fcover.png\&w=3840\&q=75\&dpl=dpl_5vKNYfy5aoaVa5a2Qcmc4t7U1FsP)](https://devin.ai/blog/more-efficient-devin) [Product](https://devin.ai/blog/more-efficient-devin) ## [Devin is now up to 40% more cost-efficient](https://devin.ai/blog/more-efficient-devin) [Devin is now 30-40% cheaper in Fusion and Normal mode, 15-20% cheaper in Ultra, and up to 70% cheaper in Devin Review, thanks to the latest models and a more efficient harness.](https://devin.ai/blog/more-efficient-devin) [September 28, 20263 min read](https://devin.ai/blog/more-efficient-devin) [Show more posts](https://devin.ai/blog/page/2)