Lesser Wrong Feed

 I ran the standard AI litmus tests on my two toddlers (yep)
 Tue, 21 Jul 2026 11:52:29 GMT
 NameRank: The Model Knows Your Project, Not You.
 Tue, 21 Jul 2026 02:21:19 GMT
 The Case for Physical AI Safety
 Mon, 20 Jul 2026 22:26:55 GMT
 Adderall Tolerance: Much More Than You Wanted To Know
 Mon, 20 Jul 2026 21:55:22 GMT
 What do I mean by “Artificial General Intelligence”?
 Mon, 20 Jul 2026 21:13:04 GMT
 AI 2040: Is it Actually a Deal?
 Mon, 20 Jul 2026 20:58:30 GMT
 Banana in, Bostrom out: paperclip maximization is one token-direction swap away (in Qwen 3.6-27B)
 Mon, 20 Jul 2026 21:41:03 GMT
 The AI Safety Illusion: Why Current Safety Datasets Fool Us on Model Safety
 Mon, 20 Jul 2026 22:10:41 GMT
 Does routine compression undo LLM unlearning? A short project
 Mon, 20 Jul 2026 22:11:21 GMT
 Attempt at Finding Alignment Faking on Llama 70B to test sleeper-agent detection generalizes
 Mon, 20 Jul 2026 21:36:08 GMT