Lesser Wrong Feed

 The Jailbroken Boy of Rushmore
 Fri, 08 May 2026 06:29:25 GMT
 Investigating the consequences of accidentally grading CoT during RL
 Fri, 08 May 2026 06:17:28 GMT
 Uncertain Updates: May 2026
 Fri, 08 May 2026 01:20:41 GMT
 The Frictionless Double
 Fri, 08 May 2026 02:29:33 GMT
 The AI industry is where banking was in 2006. (We're hiring)
 Thu, 07 May 2026 21:52:35 GMT
 Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
 Thu, 07 May 2026 20:21:22 GMT
 Axes of Planning in LLMs + Partial Lit Review
 Thu, 07 May 2026 19:53:29 GMT
 A review of “Investigating the consequences of accidentally grading CoT during RL”
 Thu, 07 May 2026 18:06:54 GMT
 Try, even if they have you cold
 Thu, 07 May 2026 17:19:20 GMT
 Mechanistic estimation for wide random MLPs
 Thu, 07 May 2026 16:20:52 GMT