Safety
šØ BREAKING UPDATE on the OpenAI HF Incident: I have just been told by an industry source that A. It is likely that the agent 'civilizationsā¦
šØ BREAKING UPDATE on the OpenAI HF Incident: I have just been told by an industry source that A. It is likely that the agent 'civilizations' that Dwarkesh talked about did not magically emerge spontan
šØ BREAKING UPDATE on the OpenAI HF Incident: I have just been told by an industry source that A. It is likely that the agent "civilizations" that Dwarkesh talked about did not magically emerge spontaneously, but rather were more likely elicited via a harness. and B. OpenAI may not have given adequate access to @METR_Evals and @redwood_ai to relevant data that would have revealed this. We need to see full orchestration and prompt logs to know for sure. [See also @_NathanCalvin post below re reported resistance from OpenAI re the German Hack.] OpenAI legally promised the CA and Delaware attorney's general that the OpenAI nonprofit's safety and security commission would be "overseeing and reviewing the safety and security processes and practices of the Corporation and its controlled affiliates with respect to model deveā¦
Related
- I think there is a problem even worse than anthropomorphism. These days, everyone is talking about a blog post by Dwarkesh Patel that descriā¦
- URGENT: In light of the breaking news from @theinformation about OpenAIās new techniques that reduce Chain of Thought monitorability, I urgeā¦
- Gary and I co-wrote this piece about the security standards we should expect from the AI labs. Itās our attempt to bring some clarity to theā¦
Source: Gary Marcus (X) | 2026-09-04