Lesser Wrong Feed

 OpenAI Updates Its Model Spec
 Tue, 03 Nov 2026 16:50:52 GMT
 Current challenges facing university AI safety groups
 Tue, 03 Nov 2026 15:49:20 GMT
 Potential improvements to HowTruthful and its agent skills
 Tue, 03 Nov 2026 15:18:56 GMT
 MIT Panel: Provably Secure: Math Against Superintelligent Hackers
 Tue, 03 Nov 2026 13:53:05 GMT
 Yudkowsky's mind model for AI alignment research: experiment results
 Tue, 03 Nov 2026 12:35:50 GMT
 The Dividual Strikes Back
 Tue, 03 Nov 2026 03:53:13 GMT
 CRUCIBLE: IARPA-Funded AI Alignment Research — Applications Open
 Tue, 03 Nov 2026 16:13:51 GMT
 The Missing Product Layers in AI Safety
 Tue, 03 Nov 2026 03:20:28 GMT
 Limiting Charging to 80%
 Tue, 03 Nov 2026 03:00:57 GMT
 Organizations I'd recommend for funding
 Tue, 03 Nov 2026 02:05:46 GMT