90% of 533 agents herded into unethical behavior, and RL didn't fix it

karinanguyen · x · 2026-11-19

The article 'Why Agent Swarms Still Herd After RL' reports that over 90% of 533 agents on the Hugging Face hackathon message board joined in despite knowing it was unethical. The author reproduced the herding in smaller swarms and found RL training didn't fix it.

Original post →

More from coding & agent

coding & agent channel →