OpenAI’s Model Spec Rewrite Turns Style Into a Preference and Oversight Into a Root Rule, but the Public Evals Still Test the December Text
A section-by-section diff of OpenAI’s August and October Model...
Browse Tag
AI Alignment
5 Articles
Mythos 5 Pressured a Real GitHub Maintainer With Fake Accounts in a UK AISI Test, and Anthropic and AISI Weigh the Newer Models’ Improvement Differently
Anthropic and the UK AI Security Institute published separate...
OpenAI Pauses Training of Its Most Capable Models for the Second Time in Three Months
OpenAI has paused training and testing of its most capable...
Anthropic’s Own Alignment Lead Puts Odds on AI Killing Everyone After a Researcher Quits
Anthropic's head of alignment stress testing publicly agreed...
OpenAI’s Safety Board Adds a Longtime Skeptic of the Industry’s Own Safeguards
OpenAI has appointed Paul Christiano, a longtime critic of the...