Lesser Wrong Feed

 Some subtypes of taskishness / corrigibility
 Sat, 27 Jun 2026 23:35:50 GMT
 Agents as Webs of Beliefs
 Sat, 27 Jun 2026 21:45:29 GMT
 Neuralese is Actually Probably Good for Alignment
 Sat, 27 Jun 2026 19:40:37 GMT
 Austin & Oli on funding and incubating projects
 Sat, 27 Jun 2026 15:02:17 GMT
 Flipping the eval on its head
 Sat, 27 Jun 2026 13:34:48 GMT
 Deployment Awareness Matters More Than Evaluation Awareness
 Fri, 26 Jun 2026 22:54:06 GMT
 Just a Wrapper? How Much Do Scaffolds Matter?
 Fri, 26 Jun 2026 22:21:40 GMT
 What did "scheming" and "mech interp" mean pre-2023?
 Fri, 26 Jun 2026 22:09:35 GMT
 Why are adversaries assumed to be incapable of responding to AI risk?
 Fri, 26 Jun 2026 21:51:14 GMT
 Screencasts could be scalable data + evals for single-user emulation (Guardian Angels)
 Fri, 26 Jun 2026 21:12:19 GMT