Cognition helps Devin test its own work with GPT‑6 Astra
Cognition's Devin now uses GPT-6 Astra to improve software testing and verify usability. The combination aims to help engineers review less code and ship more.
#编码
Today 0 items
OpenAI NewsAI score2525
GitHub Blog · AI & MLAI score4949 GitHub Copilot app for Beginners: Using the diff, terminal, and browser
The GitHub Copilot app adds three built-in panels — diff, terminal, and browser — so you can review agent code changes, run commands, and preview results without leaving the app. The diff panel highlights added and removed lines in green and red, letting you accept changes, leave comments, or ask Copilot to revise; the terminal panel supports running scripts like npm run dev with multiple windows; and the browser panel uses the Pick & Polish tool to select elements for the agent to adjust.
OpenAI NewsAI score3434 How a researcher uses Codex and ChatGPT to search for new antimicrobial molecules
César de la Fuente's lab uses Codex and ChatGPT to search the genomes of living and extinct species for antimicrobial candidate molecules to combat drug-resistant infections.
Mistral AIAI score5858 Modernizing complex legacy code with AI agents.
Mistral AI helped a European energy operator migrate 40,000 lines of Fortran 77 reservoir simulator code to C++, and shared a retrospective on the approach.
OpenAI NewsAI score2727 How GPT-5.6 Sol helps run quantum computing experiments
An MIT researcher uses GPT-5.6 Sol with Codex to autonomously run quantum computing experiments, analyze results, and calibrate qubits.
OpenAI NewsAI score3232 1Password increases engineering productivity 21% with Codex
1Password engineers use OpenAI's Codex to quickly build new features and internal tools, reaching production-grade quality under strict security policies, with engineering efficiency up 21%.
GitHub Blog · AI & MLSelectedAI score7070 Project HydraFusion: Frontier quality via multi-model orchestration
GitHub launched Project HydraFusion in research preview on GitHub Copilot CLI, using runtime multi-model orchestration to select among three execution modes — Single, Cascade, and Critique — per task, and calling models across vendors to draft, review, revise, or upgrade.
Why it matters: The article details the three execution modes, concrete benchmark comparisons, and how to get access, helping readers evaluate multi-model orchestration's impact on the cost and quality of their coding workflows.
GitHub Blog · AI & MLAI score4848 GitHub Copilot app for Beginners: Run several agents at once
The GitHub Copilot app supports running multiple AI agent sessions in parallel, with each session isolated on its own Git worktree so they don't interfere with each other and keep their own context. Users can track progress in the sessions view and switch between sessions at any time without re-explaining background. The article uses the tailspin-toys repository to demonstrate running three tasks simultaneously: adding a feature, an accessibility review, and running tests.
Hugging Face BlogSelectedAI score6262 Training a coding model to paint watercolours with TRL and OpenEnv
A Hugging Face blog author used TRL and OpenEnv to openly reproduce Surya Narreddi's approach, training Qwen/Qwen3.5-35B-A3B to write p5.brush code that paints watercolours.
Why it matters: The author has open-sourced the training recipe, environments, reference pool, and model, so readers can reproduce the entire pipeline with a single command and learn from the troubleshooting notes.
Hugging Face BlogSelectedAI score7373 Give Your Coding Agents a Memory You Own
Hugging Face has released funes, an open-source tool that turns existing agent session logs on your machine into searchable memory, supporting Claude Code, Codex, pi, and Hermes. It runs embedding and reranking locally with no account required, and can also bind to a private Hugging Face dataset for cross-machine sync. On the handoff-vs-recall benchmark, recall is 8x and 4x cheaper than writing handoff documents.
Why it matters: It is an official open-source memory layer from Hugging Face with installation instructions and benchmark comparisons, so readers can evaluate whether it can reuse their existing coding agents' session logs.
Google DeepMindSelectedAI score8686 Introducing Gemini 3.8 Flash and 3.8 Flash Cyber
Google DeepMind has released Gemini 3.8 Flash and 3.8 Flash Cyber.
Why it matters: The official release includes benchmark numbers, pricing, and real-world use cases for the two variants, so readers can assess switching costs in coding and security scenarios.
Hugging Face BlogSelectedAI score6161 Granite 4.2 LLMs: How They're Built
IBM released the Granite 4.2 reasoning model family, comprising 3B, 8B and 30B dense decoder models built on the Granite 4.1 base (pretrained from scratch on about 15T tokens, with a five-stage strategy extending context to 512K), post-trained with SFT and multi-stage GRPO reinforcement learning, all open-sourced under the Apache 2.0 license.
Why it matters: The official disclosure covers the full training pipeline from pretraining and SFT to multi-stage GRPO and agentic RL, transferable to similar model-building workflows.
Google DeepMindSelectedAI score7272 Introducing Gemini 3.7 Flash
Google DeepMind released Gemini 3.7 Flash, positioned as its flagship model for coding and agents, just three weeks after Gemini 3.6 Flash.
Why it matters: The official announcement includes multiple benchmark scores and the half-price pricing details, so readers can decide whether to switch to 3.7 Flash.
Hugging Face BlogSelectedAI score7878 Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
Meta today released Muse Glimmer, a 30B-parameter open-source multimodal model distilled from Muse under the Apache 2.0 license, aimed at privacy-focused local deployment and agentic uses like coding, document analysis, and personal assistance.
Why it matters: The article provides architecture details, agent benchmark comparisons, and day-0 usage across inference stacks, helping readers evaluate local multimodal deployment options.
Microsoft ResearchSelectedAI score7373 Orchard: An open framework for scalable agentic AI
Microsoft Research has released Orchard, an open-source agent framework built around Orchard Env, a reusable Kubernetes-based environment service supporting training and evaluation of software engineering, web navigation, and personal assistant agents, with end-to-end training directly inside real harnesses such as Codex, OpenClaw, and ZeroClaw. Orchard-SWE reaches 69.7% on SWE-bench Verified with about 3B active parameters.
Why it matters: Microsoft has open-sourced a reusable agent environment layer along with training recipes for three small models, letting readers gauge what small models can achieve on real tasks.
Berkeley AI ResearchAI score4646 Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction
Berkeley AI Research proposes the ABBEL framework, which replaces full interaction history with a natural-language belief state as the agent's working context and introduces belief grading to supervise summary content. On the CollabBench collaborative coding benchmark, ABBEL-rec-BG closes roughly 50% of the performance gap with full-context models, cuts training steps from 100 to 50, and uses significantly shorter peak context token lengths than the full-context setting.
Google DeepMindSelectedAI score7676 Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
Google DeepMind released three Gemini models: Gemini 3.6 Flash cuts output token usage by 17% versus 3.5 Flash on the Artificial Analysis Index, priced at $1.50/1M input and $7.50/1M output, with DeepSWE 49% vs 37% and OSWorld-Verified 83.0% vs 78.4%.
Why it matters: The official article gives concrete pricing, token efficiency, and multiple benchmark numbers for the three new models, and explains the deployment scenarios each targets.
Google DeepMindAI score5757 Introducing Gemini 3.5 Flash Cyber
Google DeepMind released Gemini 3.5 Flash Cyber, a lightweight cybersecurity model fine-tuned from 3.5 Flash, built to quickly find, verify, and patch vulnerabilities.
Hugging Face BlogAI score4545 ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
Hugging Face launched the open-source benchmark ScarfBench (Self-Contained Application Refactoring Benchmark), which evaluates AI agents on enterprise Java cross-framework migration tasks across the Spring, Jakarta EE and Quarkus ecosystems.
Chrome Developers · AI and BrowserAI score5858 Unlock runtime insights: Introducing third-party developer tools for Chrome DevTools for agents
Chrome officially launched third-party developer tools for Chrome DevTools for agents, letting libraries and frameworks expose runtime internal state, such as component hierarchy and server-side state, to AI agents via an event-based JavaScript API.
Google ResearchAI score4040 A New Era of Discovery: Google Research at I/O 2026
At I/O 2026, Google Research announced Gemini for Science, a set of experimental scientific tools built in collaboration with Google Cloud, Google DeepMind, and Google Labs.
Mistral AIAI score4747 AI Now Summit 2026
At AI Now Summit 2026, Mistral unveiled a full-stack AI offering for industrial engineering, partnering with Airbus, BMW and ASML across design, simulation and production while ensuring data sovereignty. Its agent product Vibe was upgraded into a unified agent that handles long-horizon multi-step work, from deep research and coding to merging PRs. A 10 MW inference data center in Les Ulis, France, is slated to come online in Q3 2026.
Mistral AISelectedAI score6969 Vibe gets to work.
Mistral launched the unified AI agent Vibe, with Le Chat fully upgraded to Vibe; existing plans, history and settings migrate automatically. Work Mode targets long-horizon multi-step tasks spanning enterprise knowledge search, data analysis, document drafting and scheduled jobs; Code Mode supports remote coding sessions, parallel runs and sandbox isolation, along with a VS Code extension and an updated CLI.
Why it matters: The official announcement fully covers Vibe's Work and Code modes, pricing and access points, letting readers assess its impact on daily workflows and coding processes.
Mistral AISelectedAI score7070 Remote agents in Vibe. Powered by Mistral Medium 3.5.
Mistral released the 128B open-weight flagship model Mistral Medium 3.5 (public preview), combining instruction following, reasoning and coding, with a 256k context window and a SWE-Bench Verified score of 77.6%. API pricing is $1.5 per million input tokens and $7.5 per million output tokens.
Why it matters: The original provides model specs, benchmark scores, pricing and the open-weight access point, useful for evaluating it for self-hosting and asynchronous coding use cases.
Google ResearchSelectedAI score6262 Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery
Google's research tool ERA uses Gemini to write and optimize scientific code, and the related paper was published in Nature today. ERA uses tree search to consider thousands of approaches and reaches expert-level performance on benchmarks in genomics, public health, satellite imagery, neuroscience, time series forecasting, and mathematics.
Why it matters: The article gives ERA's performance on benchmarks across multiple disciplines and eight application cases, letting readers understand how AI-assisted scientific computing is actually being deployed.
Google DeepMindSelectedAI score8484 Gemini 3.5: frontier intelligence with action
Google DeepMind has released the Gemini 3.5 model family, starting with 3.5 Flash, positioned for agents and coding. It outperforms Gemini 3.1 Pro on Terminal-Bench 2.1 (76.2%), GDPval-AA (1656 Elo), MCP Atlas (83.6%), and CharXiv Reasoning (84.2%), with output speed 4x that of other frontier models.
Why it matters: The official release shares 3.5 Flash's benchmark scores, availability channels, and plans for a Pro follow-up, letting readers evaluate its trade-offs for agent and coding workloads.
Google DeepMindSelectedAI score6767 AlphaEvolve: How our Gemini-powered coding agent is scaling impact across fields
Google DeepMind has released a one-year impact report on AlphaEvolve, the Gemini-powered coding agent that has expanded from pilots to multiple research and commercial domains.
Why it matters: The official report details AlphaEvolve's concrete results and figures across research and commercial settings over the past year, showing the real-world reach of this kind of algorithm-discovery agent.
Mistral AIAI score5959 Spaces: A CLI Built for Humans and Agents
Mistral AI released Spaces CLI, used for project scaffolding, development environment setup, configuration generation, and deployment to staging. Evolved from an internal tool, it serves both human developers and coding agents.
Google ResearchAI score5050 Vibe Coding XR: Accelerating AI + XR prototyping with XR Blocks and Gemini
Google introduced the Vibe Coding XR workflow, combining Gemini's long-context reasoning with the web-based XR Blocks framework. Using dedicated system prompts and code templates, it turns natural language directly into runnable Android XR apps in under 60 seconds.
Mistral AIAI score5959 Leanstral: Open-Source foundation for trustworthy vibe-coding
Mistral released Leanstral-120B-A6B (6B activated parameters), its first open-source coding agent for Lean 4 formal proof, with weights under the Apache 2.0 license and accessible via Mistral Vibe and the free labs-leanstral-2603 API endpoint.
Mistral AIAI score5757 Rails testing on autopilot: Building an agent that writes what developers won't
Mistral AI built an autonomous agent that reads Rails source files, generates or improves RSpec tests, and runs unattended in CI/CD pipelines. The agent is based on Mistral's open-source coding assistant Vibe, using a repo-level AGENTS.md, skill files divided by file type, and custom tools for RuboCop and SimpleCov.
Mistral AISelectedAI score6464 Terminally online Mistral Vibe.
Mistral has released Mistral Vibe 2.0, upgrading its terminal-native coding agent, powered by the Devstral 2 model family. New features include custom subagents, multi-option clarification before execution, slash commands to load skills, a unified Agent mode, and auto-updates.
Why it matters: The article details Vibe 2.0's features, subscription plans, and Devstral 2 API pricing, so readers can evaluate whether to switch their coding workflow.
Mistral AISelectedAI score7272 Introducing: Devstral 2 and Mistral Vibe CLI.
Mistral AI has released the open source coding model family Devstral 2, comprising the 123B Devstral 2 (modified MIT license) and the 24B Devstral Small 2 (Apache 2.0). Both support 256K context windows and score 72.2% and 68.0% on SWE-bench Verified respectively.
Why it matters: The official post covers both models' open source licenses, SWE-bench Verified scores, API pricing, and hardware requirements, so readers can assess local or on-device deployment feasibility.
Mistral AIAI score5555 Announcing Codestral 25.08 and the Complete Mistral Coding Stack for Enterprise
Mistral AI released the Codestral 25.08 code completion model, along with an enterprise coding stack that includes Codestral Embed, Devstral, and the Mistral Code IDE plugin.
Mistral AISelectedAI score6262 Upgrading agentic coding capabilities with the new Devstral models
Mistral AI, in partnership with All Hands AI, released Devstral Medium and upgraded Devstral Small to 1.1.
Why it matters: Official SWE-Bench Verified scores, pricing and licensing for both new models are provided, helping developers evaluate coding agent options.
Mistral AIAI score5353 Introducing Mistral Code
Mistral has launched Mistral Code, an enterprise AI coding assistant built on the open-source Continue project, entering private beta for JetBrains IDEs and VSCode with a general release coming soon.
Mistral AIAI score5656 Codestral Embed
Mistral AI has released Codestral Embed, its first code-specific embedding model, claiming it outperforms Voyage Code 3, Cohere Embed v4.0, and OpenAI's large embedding model on real-world code retrieval.
Mistral AISelectedAI score6969 Devstral
Mistral AI and All Hands AI have launched Devstral, an agentic large language model for software engineering tasks, released as open source under the Apache 2.0 license.
Why it matters: The official release includes model weights, API pricing, specific SWE-Bench Verified scores and deployment requirements, letting readers assess fit for local or enterprise coding scenarios.
Mistral AISelectedAI score6464 Medium is the new large.
Mistral AI released Mistral Medium 3, positioned as a new class of model with SOTA performance at 8x lower cost. It reaches or exceeds 90% of Claude Sonnet 3.7 on benchmarks, is priced at $0.4 input / $2 output per M token, surpasses Llama 4 Maverick and Cohere Command A, and can be self-deployed on 4 or more GPUs.
Why it matters: The official release provides benchmarks against Claude Sonnet 3.7, pricing, and deployment requirements, letting readers evaluate its cost-effectiveness for enterprise adoption.