Lesser Wrong Feed

 Measure Optimal AI Share of Labor Costs Instead of AI or Human-Only Performance
 Tue, 10 Nov 2026 07:18:13 GMT
 Misaligned Models Still Recognise When Their Responses Are Harmful. Can Training Make Them Care?
 Tue, 10 Nov 2026 06:03:30 GMT
 Lightcone Commons: what I funded and why
 Tue, 10 Nov 2026 05:13:48 GMT
 Live disagreements with people around me
 Tue, 10 Nov 2026 05:01:06 GMT
 OpenAtom and Elemental
 Tue, 10 Nov 2026 04:52:13 GMT
 Eyesight as a replicator, with genes as its vehicle
 Tue, 10 Nov 2026 04:47:37 GMT
 Pulling the Lever in a Subway Problem
 Tue, 10 Nov 2026 03:40:57 GMT
 Lightcone Commons: Round 1 complete, Round 2 underway
 Tue, 10 Nov 2026 01:43:15 GMT
 The Western AI safety playbook doesn’t transfer to China
 Tue, 10 Nov 2026 01:42:12 GMT
 Epistemic Sudden Death
 Tue, 10 Nov 2026 01:41:11 GMT