https://t.co/wjMMp6vg36
Chrome 146 Canary has this new thing called WebMCP behind a flag. Basically lets websites expose functions that AI agents can call directly instead of screenshotting and clicking around.
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.
https://t.co/YCvOwwjOzF
Part code, part sci-fi, and a pinch of psychosis :)
Created a tool to browse Handshake domains directly from the blockchain โ no third-party DNS.
One command starts an SPV node + HTTP proxy for Chrome: node check_hns.js proxy
Feedback appreciated! ๐
https://t.co/EVosi4YSTb
#Handshake#HNS#Web3#BuildInPublic#DNS
Just open-sourced HNS Resolver ๐ ๏ธ
A simple tool for resolving Handshake (HNS) domains โ useful for anyone building or experimenting with the decentralized naming ecosystem.
https://t.co/e3nucsFeuA
Feedback, issues, and contributions welcome! ๐
#handshake#web3#blockchain
Real example from today:
Copilot approved my CSS change on the first pass.
Claude caught that I was removing a security enforcement flag.
Different models catch different things. That's the whole point.
--all-reviewers runs every configured AI reviewer on your staged diff simultaneously.
Default mode: first available reviewer responds โ done.
All-reviewers mode: all of them review โ all must pass.
Think of it as requiring multiple approvals, but from AIs.