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.
More from coding & agent
- Open-source Dodaios orchestrates Claude Code, Codex and 7 more coding agents — InternationalGap3698 · 2026-11-19
- Notion's Ivan Zhao: context outlasts UI, and the next billion users are agents — danshipper · 2026-11-19
- Show & Tell: an MCP photo-guessing game you play against ChatGPT or Claude — ImpossibleOption8508 · 2026-11-19
- Prompt-injection filtering isn't a security boundary — enforce at the action layer — vasuman · 2026-11-19
- FrontierRSI: New Benchmark Tests Whether AI Agents Can Do Real AI Research — techNmak · 2026-11-19
- 130,000+ SEC Form 144 filings added to a dataset, revealing insider sales up to 4 days before Form 4 — virattt · 2026-11-19