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 :)
Voice mode is rolling out now in Claude Code. It’s live for ~5% of users today, and will be ramping through the coming weeks.
You'll see a note on the welcome screen once you have access. /voice to toggle it on!
New in Claude Code: Remote Control.
Kick off a task in your terminal and pick it up from your phone while you take a walk or join a meeting.
Claude keeps running on your machine, and you can control the session from the Claude app or https://t.co/er6Blrr63e
Convention over configuration set the path for 20+ years of great training data for AI to use today. Not only does this mean agents do great with Rails, but also that squishy humans can quickly and confidently review the output without a jungle of distracting boilerplate.
"Shopify is the patron saint of Ruby on Rails. Its infrastructure team is the backbone of our ecosystem, and its continued success the best case study of how far you can take this framework and language. They deserve a gawd damn parade for all they do." https://t.co/QuRCRgZW8K
🚨 Unpopular opinion: Most "AI" tools are just fancy chatbots.
Real AI should write code, not just talk about it.
Built a system using PromptEngine + RubyLLM + cursor-agent CLI headless that actually generates production Ruby parsers from PDF documents.
This is AI that ships, not AI that ships demos.
Ronald Rouse (‘25 TX) rockets this ball to deep right for a double. Clean weight transfer and keeps it back. Does a really nice job staying on this ball low in the zone. #SouthWS@PG_Uncommitted
@_LimeAID It's not bad cellular reception. I tried numerous times over a 3 day period all over San Antonio and never received a text. Try testing the signup process without a facebook account.