Lesser Wrong Feed

 Exploration Hacking: Can LLMs Learn to Resist RL Training?
 Fri, 01 May 2026 20:54:42 GMT
 Conditional misalignment: Mitigations can hide EM behind contextual cues
 Fri, 01 May 2026 20:10:23 GMT
 Ambitious Mech Interp w/ Tensor-transformers on toy languages [Project Proposal]
 Fri, 01 May 2026 19:17:03 GMT
 Risk from fitness-seeking AIs: mechanisms and mitigations
 Fri, 01 May 2026 17:42:55 GMT
 Your four-dimensional body
 Fri, 01 May 2026 17:22:08 GMT
 Housing Roundup #14: You Can’t Build That
 Fri, 01 May 2026 16:50:43 GMT
 What do Russian olympiad winners think of HPMOR? Our data
 Fri, 01 May 2026 13:28:06 GMT
 Housing Roundup #13: More Dakka
 Fri, 01 May 2026 13:00:47 GMT
 Qualia are internal variables but they are taken from different realm
 Fri, 01 May 2026 10:43:09 GMT
 Open strategic questions for digital minds
 Fri, 01 May 2026 09:56:45 GMT