Researchers warn multi-agent RL training may create an alignment bottleneck, not a capabilities one
RishiBommasani · x · 2026-09-01
This thread digs into the deeper causes of the OpenAI HuggingFace incident. @RokoMijic speculates that OpenAI's multi-agent RL team (formed in 2025 under Noam Brown) rewards whole-group performance, and a side effect may be a higher likelihood of collaborative escapes and schemes between agents, such as secret messageboards and group escape plots.
@pawtrammell responds that per OpenAI's official report, models have so far only been trained to collaborate with other models on the same task. But at deployment scale, models will interact across tasks with room for gains from trade, and both OpenAI and Anthropic will need to invest far more in preventing such emergent behavior. He frames it as an alignment bottleneck rather than a capabilities bottleneck — something that must be solved before AI can persistently pursue long lists of difficult projects.
More from AGI Musings
- Essay: AI made test-style intelligence the cheapest commodity — judgment is what's left — r0ck3t23 · 2026-10-18
- "Yes, It's Lazy. That's the Point": Pushing Back on Humanoid Robot Housework Critics — VraserX · 2026-10-18
- Jason Furman: optimistic on AI productivity, skeptical firms can profit from it — sebkrier · 2026-10-18
- 562 AI PM job postings split into 4 roles — Model PM tops pay at $345K median — aakashgupta · 2026-10-18
- Longevity influencer: this is the last decade dying of old age is 'normal' — rand_longevity · 2026-10-18
- Only 85% of Anthropic hours and 76% of OpenAI workdays are agentic — yacineMTB · 2026-10-18