Yoonho Lee(@yoonholeee):How can we autonomously improve LLM harnesses on problems humans are actively working on? Doing so requires solving a hard, long-horizon credit-assignment problem over all prior code, traces, and scores. Announcing Meta-Harness: a method for optimizing harnesses end-to-end

Yoonho Lee

@yoonholeee

Final-year ML PhD @StanfordAILab + SR at Google. Trying to make text optimization work.

加入 March 2017

665 正在關注 5K 粉絲

Yoonho Lee@yoonholeee

2026.03.30 15:32

How can we autonomously improve LLM harnesses on problems humans are actively working on? Doing so requires solving a hard, long-horizon credit-assignment problem over all prior code, traces, and scores. Announcing Meta-Harness: a method for optimizing harnesses end-to-end