My benchmark for agents that fake "done" kept catching my own harness instead
This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked A month ago I was driving an agent harness with a free model and asked it to sort a folder. Twenty seconds later it reported the job finished. It had moved zero files. An error would have been fine. An error gets looked a…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-09-25 15:13 · DEV Community — Machine Learning
My benchmark for agents that fake "done" kept catching my own harness instead