Follow AI Builders — Not Influencers
loved this from @karpathy over the weekend I built "autoresearch but for agents" Same idea — give an AI coding agent your agent code + an eval dataset, let it experiment autonomously overnight. It modifies the code, runs evals via LangSmith, keeps improvements, discards regressions. You wake up to a better agent. Bring your own agent (any framework or none), dataset, and eval metrics. https://github.com/hwchase17/autoresearch-agents
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
RT Sarah Chieng [Technical] Write & Learn #3 coming up w/ @swyx @byAnhtho > at the new @KernelLabs_ai office > 30 spots > apply at https://partiful.com/e/bUWru87loS2336UvRFiq Original tweet: https://x.com/SarahChieng/status/2031062711430197629
more saturday morning writing with friends ✍️ @QuinnyPig @swyx @dexhorthy @dylan522p @alyciazcary @chongz @brainstub @elephant_lumps @emilyhanyf @darkproger @JuanPa @mattyp @sberens @swunicorn
