Andrej Karpathy has released autoresearch, an open-source project that lets an AI agent autonomously run, evaluate and iterate on machine learning training experiments on a single GPU, keeping only the changes that measurably improve a model. The MIT-licensed repository provides a deliberately minimal scaffold in which a coding agent edits training code, runs a fixed-length experiment, scores the result, and either commits the improvement to Git or resets — a loop that can be repeated dozens of times per hour without human intervention.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.