How Meta-Harness Enables AI to Self‑Optimize Its Own Harness
Meta-Harness, an open‑source framework from Stanford's IRIS lab, lets large language models access their full code, execution traces, and evaluation scores to autonomously improve prompting pipelines, achieving state‑of‑the‑art results on TerminalBench‑2 while exposing challenges such as long evaluation time, massive token generation, and specialized storage needs.
