Lesser Wrong Feed

 Why Many Ambitious (and Altruistic) People Probably Undervalue Their Happiness
 Sun, 08 Mar 2026 02:31:03 GMT
 The current SOTA model was released without safety evals
 Sun, 08 Mar 2026 01:51:06 GMT
 Mitigating collusive self-preference by redaction and paraphrasing
 Sat, 07 Mar 2026 21:54:13 GMT
 Proposal For Cryptographic Method to Rigorously Verify LLM Prompt Experiments
 Sat, 07 Mar 2026 21:09:11 GMT
 The first confirmed instance of an LLM going rogue for instrumental reasons in a real-world setting has occurred, buried in an Alibaba paper about a new training pipeline.
 Sat, 07 Mar 2026 20:18:15 GMT
 When has forecasting been useful for you?
 Sat, 07 Mar 2026 19:50:40 GMT
 Can governments quickly and cheaply slow AI training?
 Sat, 07 Mar 2026 19:11:22 GMT
 Did I Catch Claude Cheating?
 Sat, 07 Mar 2026 13:24:15 GMT
 D&D.Sci Release Day: Topple the Tower!
 Sat, 07 Mar 2026 02:48:50 GMT
 AI Safety Needs Startups
 Sat, 07 Mar 2026 01:27:54 GMT