Lesser Wrong Feed

 SLT for AI Safety
 Tue, 01 Jul 2025 04:52:21 GMT
 Problematic Professors
 Tue, 01 Jul 2025 05:59:39 GMT
 I can't tell if my ideas are good anymore because I talked to robots too much
 Tue, 01 Jul 2025 02:26:21 GMT
 The best simple argument for Pausing AI?
 Mon, 30 Jun 2025 20:40:51 GMT
 Hiring* an AI** Artist for LessWrong/Lightcone
 Mon, 30 Jun 2025 19:01:57 GMT
 SAE on activation differences
 Mon, 30 Jun 2025 17:50:54 GMT
 The Spectrum of Attention: From Empathy to Hypnosis
 Mon, 30 Jun 2025 17:42:25 GMT
 Substack and Other Blog Recommendations
 Mon, 30 Jun 2025 17:20:03 GMT
 What We Learned Trying to Diff Base and Chat Models (And Why It Matters)
 Mon, 30 Jun 2025 17:17:42 GMT
 Project Vend: Can Claude run a small shop?
 Mon, 30 Jun 2025 15:22:25 GMT