The Oracle’s Gift
Published on October 8, 2025 8:13 PM GMTI have tried and failed many times to…
Category: Opinion
Thinking Mathematically – Convergent Sequences
Published on October 8, 2025 7:44 PM GMTThis is a prototype attempt to create lessons…
The Relationship Between Social Punishment and Shared Maps
Published on October 8, 2025 7:38 PM GMTA punishment is when one agent (the punisher)…
Plans A, B, C, and D for misalignment risk
Published on October 8, 2025 5:18 PM GMTI sometimes think about plans for how to…
Heaven, Hell, and Mechanics
Published on October 8, 2025 11:05 AM GMTThese frames are all justified:Hell: The world is…
You Should Get a Reusable Mask
Published on October 8, 2025 2:40 AM GMT A pandemic that's substantially worse than COVID-19…
Replacing RL w/ Parameter-based Evolutionary Strategies
Published on October 8, 2025 1:02 AM GMTI want to highlight this paper (from Sept…
Intent alignment seems incoherent
Published on October 7, 2025 11:01 PM GMTThis post is part of the sequence Against…
The Tower of Babel in Reverse
Published on October 7, 2025 4:27 PM GMTThis was originally posted on my Substack TOP SECRET//SCI//SAP//ORCON//NOFORNRef:…
Petri: An open-source auditing tool to accelerate AI safety research
Published on October 7, 2025 8:39 PM GMTThis is a cross-post of some recent Anthropic…