Dev trains a tiny 2B model just for FunSearch, then gives it a shell tool

cephaloform · x · 2026-11-21

Developer @cephaloform shows off a 2B model trained specifically for FunSearch — an early auto-research harness that even works on base models — now equipped with tools including shell access. The takeaway: an autonomous research loop can be squeezed into a tiny specialized model instead of relying on frontier-size LLMs.

Original post →

More from coding & agent

coding & agent channel →