Viewing profile — gopalraja

Really good points Lillian. Agreed on keeping the evaluator outside the loop that evolves the harness. One practical failure mode I’ve have experienced in my agentic harness tasks …

[flagged]

Yeah, fair question. I read this less as “build a decompiler with an LLM instead of training one to decompile,” and more as a different loop: you still get an artifact you can meas…