LessWrong (30+ Karma)

“War Claude” by PeterMcCluskey

“How to Design Environments for Understanding Model Motives” by gersonkroiz, aditya singh, Senthooran Rajamanoharan, Neel Nanda

“Tools to generate realistic prompts help surprisingly little with Petri audit realism” by Connor Kissane, Monte M, Fabien Roger

“OpenAI employees: Now is the time to stop doing good work.” by bhauth

“An Open Letter to the Department of War and Congress” by Gordon Seidoh Worley

“Introducing and Deprecating WoFBench” by jefftk

“I’m Bearish On Personas For ASI Safety” by J Bostock

“Coherent Care” by abramdemski

Decision theory requires a shift from the traditional advice-giving model toward a design-oriented framework to effectively evaluate decision procedures. By treating decision procedures as components within a decision problem, one can apply calibration conditions—specifically observation and subjective state calibratio...

[Linkpost] ”“Fibbers’ forecasts are worthless” (The D-Squared Digest One Minute MBA – Avoiding Projects Pursued By Morons 101)” by Random Developer

“Schelling Goodness, and Shared Morality as a Goal” by Andrew_Critch

“Anthropic and the DoW: Anthropic Responds” by Zvi

The central issue is the conflict between Anthropic and the Department of War (Dow) over the use of AI, specifically Claude, in military applications. Anthropic refuses to remove safeguards against mass domestic surveillance and fully autonomous weapons, leading to the Dow threatening to label them a supply chain risk....

“Getting Back To It” by sarahconstantin

“New ARENA material: 8 exercise sets on alignment science & interpretability” by CallumMcDougall

“Sam Altman says OpenAI shares Anthropic’s red lines in Pentagon fight” by Matrice Jacobine

“Strategic nuclear war twice as likely to occur by accident than by AI decisions according to new study” by kromem

“Why Did My Model Do That? Model Incrimination for Diagnosing LLM Misbehavior” by aditya singh, gersonkroiz, Senthooran Rajamanoharan, Neel Nanda

“Here’s to the Polypropylene Makers” by jefftk

“Anthropic: “Statement from Dario Amodei on our discussions with the Department of War”” by Matrice Jacobine

“Schmidt Sciences’ request for proposals on the Science of Trustworthy AI” by James Fox

“AI #157: Burn the Boats” by Zvi