AI for Human Reasoning for Rationalists
Published on February 3, 2026 1:22 PM GMTToday’s humanity faces many high stakes and even…
Category: Opinion
Conditionalization Confounds Inoculation Prompting Results
Published on February 3, 2026 11:50 AM GMTSummaryConditionalization in Inoculation Prompting. Inoculation Prompting is a…
The Atoms of Knowledge Aren’t Universal
Published on February 3, 2026 10:52 AM GMTWhy DeSci should stop searching for universal verification…
What did we learn from the AI Village in 2025?
Published on February 3, 2026 9:52 AM GMTWhy This Project ExistsStandard AI benchmarks test narrow…
Thought Editing: Steering Models by Editing Their Chain of Thought
Published on February 3, 2026 9:51 AM GMTTL;DRWe steer reasoning models by editing their chain…
Increasing AI Strategic Competence as a Safety Approach
Published on February 3, 2026 1:08 AM GMTIf AIs became strategically competent enough, they may…
On Goal-Models
Published on February 2, 2026 6:44 PM GMTI'd like to reframe our understanding of the…
“Features” aren’t always the true computational primitives of a model, but that might be fine anyways
Published on February 2, 2026 6:41 PM GMTOr, partly against discussion about generic “features” in…
“Features” aren’t always the true computational primitives of a model, but that might be fine anyways
Published on February 2, 2026 6:41 PM GMTOr, partly against discussion about generic “features” in…
Are there lessons from high-reliability engineering for AGI safety?
Published on February 2, 2026 3:26 PM GMTThis post is partly a belated response to…