Kushagra

Tomorrow, we’re introducing you to your new vibe design partner. 🤝 Our biggest update ever drops tomorrow. 👀👇

A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks.

The cofounder and CTO of Perplexity, @denisyarats just said internally at Perplexity they’re moving away from MCPs and instead using APIs and CLIs 👀

Knowledge work was built around scarcity of information.Agents just ended that. Research, analysis, writing, synthesis the core loops of knowledge work can now run autonomously. The scarce skills now: taste, judgment, problem selection.

Ai for code, Ai for debugging, Ai for review 😇

Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.

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 :)

Say hello to Rae

Escape

Last option

Claude is everywhere 🙏🏻

Late night rides

Sometimes AI is crazy

Locked in

Rough day

Let my intrusive thoughts win

What’s stopping you from coding like this

Damn

What are you guys doinn ??