HF researcher: doing is harder than criticising — agent workflows should leverage both roles

antoine_chaffin · x · 2026-09-21

Hugging Face researcher antoinechaffin argues that doing is harder than criticising, which is why GANs and RL work. He suggests we should lean into this more in agentic workflows by using models for both generating and judging.

Original post →

More from coding & agent

coding & agent channel →