Lesser Wrong Feed

 Do your readers get annoyed if you post every day for 30 days?
 Mon, 17 Aug 2026 21:59:24 GMT
 What 27 AI Safety Generalists Are Building This Summer
 Mon, 17 Aug 2026 21:56:55 GMT
 What gives you away: how LLMs form opinions of you
 Mon, 17 Aug 2026 21:11:25 GMT
 Evaluating Chain-of-Thought Monitorability is Still an Open Problem: Comments on OpenAI's Monitorability Evals
 Mon, 17 Aug 2026 19:46:43 GMT
 Weird Re-Tokenization, Symmetries and Compression: Research Agenda
 Mon, 17 Aug 2026 19:43:34 GMT
 Fork Around and Find Out Part 3: Interpreting the knight auditor
 Mon, 17 Aug 2026 18:11:10 GMT
 Connect to your future selves
 Mon, 17 Aug 2026 14:57:44 GMT
 Lateral Workshop Applications: A Case Study
 Mon, 17 Aug 2026 10:38:23 GMT
 Untie Squared ReLU variant
 Mon, 17 Aug 2026 07:04:54 GMT
 Study Update: Does post-training quantization change welfare-relevant indicators in open-weight language models?
 Sun, 16 Aug 2026 21:11:53 GMT