Highlights from Explaining AI Explainability
Published on October 24, 2025 5:22 PM GMTConor Griffin interviewed Been Kim and Neel Nanda…
Category: Opinion
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
Published on October 24, 2025 5:21 PM GMTTL;DRCoT monitoring works well when models aren't trying…
Dollars in political giving are less fungible than you might think
Published on October 24, 2025 3:54 PM GMTI used to think that a dollar in…
LW Reacts pack for Discord/Slack/etc
Published on October 24, 2025 1:20 PM GMTEver wanted to say Scout Mindset to someone…
AI Timelines and Points of no return
Published on October 24, 2025 11:15 AM GMTIn this essay, I introduce two Points of…
Can we steer AI models toward safer actions by making these instrumentally useful?
Published on October 24, 2025 9:18 AM GMTThis is the first research release from Wiser…
Introducing ControlArena: A library for running AI control experiments
Published on October 24, 2025 9:51 AM GMTThis has been a collaborative effort between UK…
Plan 1 and Plan 2
Published on October 24, 2025 8:18 AM GMTMax Tegmark recently published a post "Which side…
Why I Don’t Believe in True AGI
Published on October 24, 2025 5:24 AM GMTAlt.Title: It's the Body That Matters in the…
Guys I might be an e/acc
Published on October 24, 2025 3:25 AM GMTI read If Anyone Builds It, Everyone Dies…