Lesser Wrong Feed

 [Linkpost] Thoughts on the Recent OpenAI Hack
 Fri, 24 Jul 2026 01:51:51 GMT
 Should OpenAI's rogue agent be punished?
 Fri, 24 Jul 2026 01:20:53 GMT
 Evaluating Red Team and Blue Team Capability for AI Control Research
 Fri, 24 Jul 2026 01:11:40 GMT
 Fixing rewards for NLA to reduce confabulation
 Fri, 24 Jul 2026 00:57:58 GMT
 Anthropic's J-Lens: A Research Engineer's Analysis
 Fri, 24 Jul 2026 00:57:19 GMT
 Pulling the Fire Alarm
 Thu, 23 Jul 2026 23:14:00 GMT
 Contra George Hotz on "AI 2040 and the Cult of Intelligence"
 Thu, 23 Jul 2026 22:44:38 GMT
 The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
 Thu, 23 Jul 2026 22:37:46 GMT
 vibes-based thinking as a cultural response to unknowns
 Thu, 23 Jul 2026 22:39:28 GMT
 Red-teaming LLM unlearning: LUNAR's "forgotten" knowledge is still recoverable
 Thu, 23 Jul 2026 21:51:57 GMT