devscourtAI

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the prompt (.md) - the AI agent iterates on the training code (.py) The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc. github.com/karpathy/autor… Part code, part sci-fi, and a pinch of psychosis :)

We're launching Claude Community Ambassadors. Lead local meetups, bring builders together, and partner with our team. Open to any background, anywhere in the world. Apply: claude.com/community/amba…

We rebuilt Next.js in a week. No, really. The team ported the framework to run natively on Workers to prove what’s possible with edge-first architecture. Dive into the technical hurdles we solved to eliminate Node.js dependencies. cfl.re/4ciNc3L

Gemini 3.1 Pro is our new baseline for complex problem-solving. This model represents a major leap in core reasoning, verified by a 77.1% score on the ARC-AGI-2 benchmark — which tests the ability to solve brand-new logic patterns. That’s more than double the performance of 3 Pro.

Today, we’re releasing Gemini 3.1 Pro. It’s the same core intelligence that powers Gemini 3 Deep Think, now scaled for your practical applications. It’s a smarter model for your most complex tasks. See 3.1 Pro in action 🧵↓

Additionally, code execution, web fetch, memory, programmatic tool calling, tool search, and tool use examples are now generally available. Read more: claude.com/blog/improved-…

Today, we’re releasing a significant upgrade to our specialized reasoning mode, Gemini 3 Deep Think. Deep Think is built to drive practical applications, enabling researchers to interpret complex data and engineers to model physical systems through code. With the updated Deep Think, you can turn a sketch into a 3D-printable reality. Deep Think analyzes the drawing, builds the complex shape, and generates a file so you can create the physical object with 3D printing. This is rolling out now to Google AI Ultra subscribers. Select the "Deep Think" option in the tools menu to get started. Learn more here: goo.gle/3MoiifF

You told us you’re running multiple AI agents and wanted a better UX. We listened and shipped it! Here’s what’s new in the latest @code release: 🗂️ Unified agent sessions workspace for local, background, and cloud agents 💻 Claude and Codex support for local and cloud agents 🔀 Parallel subagents 🌐 Integrated browser And more...

@matt_elevenlabs 11B

We just raised $500M at an 11B valuation 🎉 To celebrate, we’re giving away 1,000 free credits so you can test our platform. For the next 6 hours, comment “11B” below and we’ll DM you the credits (must follow) 👇

Vibe coding is the new product management. Training and tuning models is the new coding.

Introducing ElevenLabs Skills. With skills, AI coding assistants like Claude Code, Cursor, and OpenCode are better at using our APIs to handle AI audio and agent workflows. Get started: npx skills add elevenlabs/skills

Wild. By far the most complete Claude Skills repo yet 🤯 @Composio’s Awesome-Claude-Skills packs 100`s of ready-to-use workflows: ↳ PDF tools, changelog generation ↳ Playwright automation ↳ AWS/CDK tools, MCP builders ... and much more! Free and open-source. Repo in 🧵↓

🎄 We've shipped Skills for Vibe CLI: your dev expertise and rules, bundled and reusable across projects. Plus reasoning model support and native terminal themes. Try Vibe CLI now and happy shipping! → uv tool install mistral-vibe

Introducing A2UI: Agent-to-User Interface 🛜Protocol for agent-driven interfaces 🤖Enables agents to generate interactive user interfaces 🐙Open source github.com/google/A2UI/

Prompting GPT-5.2 Codex for long-running tasks:

We’ve rewritten Claude Code’s terminal rendering system to reduce flickering by roughly 85%. We wanted to share more about why this was so difficult, how the fix works and how we used Claude Code to fix it 🧵

Just launched GPT-5.2-Codex! The best model for long-horizon agentic coding, including strong performance on refactors and migrations. Codex becoming very magical.

I love the expression “food for thought” as a concrete, mysterious cognitive capability humans experience but LLMs have no equivalent for. Definition: “something worth thinking about or considering, like a mental meal that nourishes your mind with ideas, insights, or issues that require deeper reflection. It's used for topics that challenge your perspective, offer new understanding, or make you ponder important questions, acting as intellectual stimulation.” So in LLM speak it’s a sequence of tokens such that when used as prompt for chain of thought, the samples are rewarding to attend over, via some yet undiscovered intrinsic reward function. Obsessed with what form it takes. Food for thought.