Simple Meta-Harness on Islo.dev
Yossi Eliaz; Eliaz; Yossi
A harness is the prompt + tools + scaffolding around an LLM agent. A
meta-harness is the loop that improves the harness automatically: a proposer
agent reads the diagnostic logs of prior candidates, spots a failure mode, and writes a
better harness. Yoonho Lee’s
framing of the idea makes one sharp
claim — the bottleneck is diagnostic context: most optimizers
compress prior runs into summary statistics, while meta-harness gives the proposer up
to 10M tokens of raw execution traces to...