Largest open experiment yet on autonomous agents iterating in a research environment

eliebakouch · x · 2026-09-09

eliebakouch announces what he claims is the largest open experiment on autonomous agents iterating on a research environment, scaling runtime, compute, and diversity of models and harnesses.

For comparison, similar tasks in system cards — Anthropic's "optimizing an LLM training on CPU" and OpenAI's GPT-5.6 on nanogpt track 1 — ran for less than a day. The project shares extensive details including traces and scratchpads, with more results coming.

Original post →

More from coding & agent

coding & agent channel →