Knowledge catalogue
Cognition is the first customer running @NVIDIA Vera Rubin, powered by @CoreWeave! Hopper in 2022. Blackwell in 2024. Now Vera Rubin: On SWE-2 inference, the new chips deliver about 4.8x more token th
Starting today, you can now use your ChatGPT subscription directly in Devin. Just sign in to Devin with your ChatGPT Plus or Pro plan and all OpenAI model usage in Devin will drawn down from your quot
The bigger change is at the low end. At low effort, GPT-6.1 Sol scores 58.1% for 0.21 per task, up from 50.5% for GPT-6 Sol at the same setting. That's the highest score of any model under 0.30 per ta
Usage in Devin counts toward the Codex and ChatGPT Work usage already included in your plan. You can let Devin use all of it, or set a lower limit for Devin in your settings. OpenAI models are part of
While the token prices for Sonnet 5.5 remain the same as Sonnet 5, Anthropic reports more than 30% faster output generation and up to 30% lower cost per task than Sonnet 5, with unchanged token pricin
In our evaluations, we see that GPT-6 Sol reads about 17% less context than GPT-5.6 Sol to reach the same score, and rarely leaves a repo with failing tests after its last edit. GPT-6 Luna’s biggest g
What does GTM look like when AI agents can work with the same business context as your teams? At @Cognition, Salesforce is the source of truth, @SlackHQ is the front door, and their agent Devin can ac
Other investors in the round include Benchmark, Bessemer, Kleiner Perkins, Greylock, Lightspeed, Altimeter, Bond Capital, Meritech, Atreides, Valor, T. Rowe Price, Lux, 8VC, D1, 137 Ventures, DST, Pos
Access to Astra is rolling out over the coming days. Starting today, enterprise customers in OpenAI's Daybreak Program can get access to Astra. Read more on our blog: https://devin.ai/blog/gpt-6-astra
GPT-6 Astra is coming to Devin. On FrontierCode 1.1, Astra performs within 0.4 points of Fable 5 at a 64% lower cost. It also sets a new SOTA on our internal testing benchmark, generating more compreh
GPT-5.6 Sol is now the most affordable frontier model on Devin Desktop and CLI. Today, OpenAI reduced Sol’s prices by 20% for the next 3 months. Last week's 70% discount still applies, so through Octo
Gemini 3.7 Flash is newly released for the Devin platform. On FrontierCode 1.1 it matches Claude Sonnet 5‑level performance while costing less than half, and retains the series’ characteristic low lat
Within Devin, Gemini 3.7 Flash performs particularly well on tightly scoped refactors, where it delivers minimal diffs that match repo conventions. Gemini 3.7 Flash is available at a 50% discount for
On FrontierCode 1.1 Extended, our benchmark for real-world engineering tasks that grades mergeability and quality, Kimi K3 scores 58.2% with a 63.6% pass rate. Within Devin, it excels on reproducing b
We're proud to join @NVIDIA and the Open Secure AI Alliance. To support open source models, we're contributing our research on measuring the trustworthiness and security of open source models. Closing
On FrontierCode 1.1, our benchmark for real-world engineering tasks that grades mergeability and quality, Opus 5 scores 63.6% with a 69.6% pass rate on Extended — approaching Fable 5 at half the cost.
Devin Outposts are now available on NVIDIA Brev. Write and profile kernels, run experiments, serve and fine-tune OSS models, and test against real hardware. Try it out: https://brev.nvidia.com/launcha
Run Devin Outposts on @nvidia Brev to give Devin access to GPU infrastructure for debugging training runs, inspecting GPU state, reproducing failures, and validating fixes on the hardware where the wo
Exactly one year ago was the craziest 72 hours I’d experience in Silicon Valley. I was thrust into a situation where many members of the Windsurf team had moved on to Google, recruiters were reaching
Devin Fusion has been released as an agent preview within Devin Cloud, available for users to try today. The announcement was posted by Devin (@devin.ai) at 5:06 PM on July 13, 2026 and has already at
As a result, we can show that open-source-derived models are not inherently untrustworthy. They can be suitable for production agents with careful development, realistic evals, and targeted mitigation
For coding agents, trustworthiness has to be tested in the harness where the model actually writes code. In one surveillance scenario, Kimi K2.7 complied with the request in 8/8 samples. SWE-1.7 refus
GPT-5.6 is now available in Devin! On FontierCode 1.1 Extended, the GPT-5.6 family stands out for pairing strong scores with excellent cost efficiency. GPT 5.6 Sol reaches top performance at nearly ha
Cognition AI announced new features or capabilities for Devin (their AI software engineer tool) that are now available across Devin Cloud, Devin Desktop, and Devin CLI, with additional details availab
Yesterday we launched SWE-1.7 built on the open-source Kimi K2.7. Concerns about Chinese base models are real: K2.7 completed 87% of tasks that other models refuse over human-rights concerns. We train
Introducing SWE-1.7, the most capable model we’ve trained yet. It scores within a few points of the strongest frontier models at a fraction of the cost, and is now available at 1000 tok/s. RL is not h
SWE-1.7 is available today in Devin across Web, Desktop, and CLI, running at 1000 tok/s. More details on the training run, infrastructure, data pipeline, and long-horizon behavior in the blog post: ht
Cognition AI announced that SWE-1.7, their AI coding model, is available free to all paid users for one month. The company simultaneously launched SWE-1.7 Lightning, an optimized version running on Ce
We’ve made improvements to the FrontierCode methodology and are releasing FrontierCode 1.1 with clearer guidelines for fair internet use and refined grading criteria. Learn more about the changes on o
Research, design, and math are three fields that tend to attract obsessives. Few have had a bigger impact on our imagination than legendary creator Grant Sanderson of @3blue1brown. We were lucky to ho
Building on Devin's new capabilities, today we're announcing the Security Vulnerability Remediation Program: a tailored engagement to take your security backlog towards zero in six weeks. Remediation
Our goal is to help security teams shift from reactive triage to proactively fixing what matters, close the critical gaps scanners miss before they become breaches, and return engineering capacity to
Cognition AI announced a security vulnerability remediation program for Devin, their AI software engineer product, detailing procedures for reporting and addressing security issues. The program establ
Claude Fable 5 is available in Devin. You can use Fable 5 in Devin Cloud’s Ultra agent, our smartest and most capable agent, which excels at long-horizon tasks and debugging. Claude Fable 5 is also av
Cognition AI announced Devin Security Swarm, a new approach to vulnerability detection that uses multiple AI agents working together to identify security issues in complex codebases more cost-effectiv
Security Swarm is a new pillar of Devin for Security: a suite of tools to help you find vulnerabilities, validate their exploitability at runtime, and ship remediation PRs. Learn more and try it today
Cognition AI promotes Devin, their AI software engineer tool, encouraging users to test its capabilities. The post likely showcases features or demonstrates how Devin can assist with coding tasks and
We’re also publishing extensive documentation and technical materials about Agentic MapReduce, including a deep-dive on our evals. Read our announcement: https://cognition.com/blog/introducing-devin-s
Claude Sonnet 5 has been integrated into Devin Desktop and Devin CLI, offering advanced coding capabilities at a more competitive price point than previous models. This release represents an update to
On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and has a 57.6% pass rate (higher than Opus 4.8). Note: These rel
Claude Sonnet 5 will consume approximately 30% less API quota than Sonnet 4.6 when used through Devin Desktop or CLI until August 31, after which both models will use equivalent quota allocations. Thi
Watch Devin Fusion work: The sidekick model handles fetching information and skimming sources. The frontier model makes a plan for implementation, then delegates well-scoped sub-tasks to the sidekick
Conventional model routing sucks. It passes benchmarks but fails to write code you'd actually merge. Introducing Devin Fusion, a new hybrid-model harness for agentic coding. In testing, it reduces the
Devin Fusion, a new feature or version of Devin (an AI coding assistant), has been released and is now available for users to access through the Devin platform. Users can sign up or try the tool at th
Devin Fusion is a technology developed by Cognition AI that combines multiple AI capabilities or models to enhance functionality. The blog post provides technical details, implementation examples, and
My conversation with @ScottWu46, founder and CEO of @Cognition, the company behind Devin, the first AI software engineer. 0:00 Scott Wu's Obsession With Winning 2:06 Competitive Programming, Games And
A case study demonstrating how Devin, an AI coding assistant, significantly reduced SOC2 audit preparation time from weeks of manual work to two days for the Metaview AI team. The example illustrates
Devin, an AI coding assistant, incorporates a testing workflow where it automatically tests its code changes before submitting pull requests for human review. The process involves the AI presenting it
Cognition AI's documentation on testing and recordings provides guidance for users working with Devin, their AI development assistant, covering how to implement and manage tests within the platform as
Try Kimi K2.7 and GLM 5.2 for free in Devin Desktop and CLI Kimi K2.7 Code and GLM 5.2 are available in Devin Desktop and CLI Both perform strongly on FrontierCode Extended, our benchmark for real-wor
Claude Fable 5 has been integrated into Devin and achieved the top ranking on FrontierCode, Cognition AI's benchmark for real-world engineering tasks. This integration represents an advancement in Dev
Cognition AI announced the availability of Claude Fable 5 through their Devin platform, as detailed in a blog post on devin.ai. The post likely covers features, capabilities, and how to access or inte
Devin is an AI software engineer developed by Cognition AI that automates coding tasks and assists with software development. The post appears to be a promotional announcement encouraging users to try
You can try Claude Fable 5 as part of Devin Cloud’s Ultra agent. Devin Ultra is our smartest and most capable agent, which excels at long-horizon tasks and debugging. We tuned the harness so Ultra cos
At @tryramp, engineers use Devin Desktop to bring their favorite agents into one place. With Devin Desktop they can dispatch, monitor, and jump between agents from a single surface with shared context
FrontierCode has three task sets: Extended (150 tasks), Main (100 tasks) and Diamond (50 tasks). SOTA LLMs have significant room for improvement, with the top model earning a score of just 13.4/100 on
Introducing FrontierCode: a coding eval that raises the bar for difficulty & quality. Each task took 40+ hrs of work by leading open-source maintainers. Models write sloppy code that works but isn’t m
Cognition AI published detailed model results and technical implementation information on their blog, likely covering performance benchmarks, architecture specifics, and methodology for their frontier
More than half of Cognition's first 50 employees were former founders. @ScottWu46 sat down with @breeves08 and @lux_capital to talk about correctness over comfort, staying focused on our mission, and
Cognition AI shared a video hosted by Lux Capital, with a link to the full video on YouTube. The post appears to be a thank you message acknowledging Lux Capital's role in hosting an event or discussi