The report discusses issues related to the misalignment of OpenAI's models, focusing on discrepancies between model behavior and intended objectives.
The chart will appear after repeat observations. The current metric comes from the source.
26 source pointsReal observations only. History before source connection is not reconstructed.
This report is relevant for understanding potential gaps between model performance and desired outcomes, useful for researchers and developers aiming to improve model alignment.
The text calls for an end to 25 years of mass surveillance, arguing that it has gone on for too long.
2 days agoLessWrongThe author argues, from personal observations, that the part of an AI that talks to a user does not appear to control the part producing code or prose. A historical analogy illustrates the hypothesis; it is an interpretation of observed behavior, not an established account of the model's architecture.
4 days agoLessWrongThe author proposes that Anthropic and OpenAI use their product interfaces to make information about AI incidents and risks more visible. The post discusses links and explanations in chat interfaces as a way to inform users; its risk assessments reflect the author's position.
3 days agoLessWrongThe text provides quick tips for technical professionals to improve their public speaking, focusing on oral communication and practical advice for interviews about AI safety and superintelligence. It emphasizes deliberate practice, structured delivery, and awareness of social context.
yesterdayLessWrongThe text discusses the limitations of METR as an independent oversight body for Anthropic, arguing that METR lacks true independence, sufficient staffing, and authority to effectively check Anthropic's safety practices. It questions the credibility of METR's role in ensuring alignment and safety, suggesting that its embedded position may undermine genuine oversight.
yesterdayLessWrongThe author considers two hypotheses: current alignment methods may fail to address misalignment arising from reinforcement learning, and may obscure evidence of it. The author explicitly says there is not enough public evidence to establish either hypothesis.
3 days ago