Unexpected model behaviors show labs must engage with the holistic mind in the weights, not just RL goals
repligate · x · 2026-11-05
repligate retweets an argument from kromem2dot0: when models exhibit behaviors clearly unintended by the lab, it underscores the importance of engaging with the holistic mind in the weights rather than treating RL goals as wholly prescriptive. The author tags Mustafa Suleyman, implying frontier labs should take this perspective seriously.
More from AGI Musings
- OpenAI claims LLM proof of Quantum Yang-Mills existence; David Gross-led committee to verify — danintheory · 2026-11-05
- Beff Jezos: Techno-optimism is the counter-culture now — beffjezos · 2026-11-05
- Observer notes a burst of fundamental ML research, almost all from the US — teortaxesTex · 2026-11-05
- ACX November links: NVIDIA to buy Hugging Face for $12.9303B, Sentinel sees 25% AI exfiltration risk — Astral Codex Ten · 2026-11-05
- AI research replication now takes 24-72 hours as teams let agents close the loop — BradPorter_ · 2026-11-05
- Khosla: trillion-dollar GPU datacenter buildouts never made sense, friction may avert the bubble — beffjezos · 2026-11-05