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.
More from coding & agent
- evmscope MCP server ships 20 blockchain tools for AI agents across 5 EVM chains — modelcontextprotocol · 2026-09-21
- The Latent Space adds agent registry, Elo duels and x402 credit economy — modelcontextprotocol · 2026-09-21
- ChatGPT co-creator's Jev: batch decisions without long LLM calls — DrDatta_AIIMS · 2026-09-21
- Qwen3.8-Flash-Next runs 3 hours locally to one-shot a 3D space shooter game — Thin_Pollution8843 · 2026-09-21
- ττ-bench: Best Coding-Agent Setup Passes Just 23.9% of Real Client Simulations — rohanpaul_ai · 2026-09-21
- Dev Launches Made With Jev, a Free Directory Cataloging Demos, Tools and Skills for the New Model — Sea_Supermarket_5891 · 2026-09-21