Graph Generator | AppPages | Russian fonts demo
Resources | Less Wrong | Action Log
[Fiction] A Confession
Thu, 18 Apr 2024 16:28:48 GMT Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight
Thu, 18 Apr 2024 16:17:41 GMT Cooperation is optimal, with weaker agents too - tldr
Thu, 18 Apr 2024 15:03:47 GMT How to coordinate despite our biases? - tldr
Thu, 18 Apr 2024 15:03:18 GMT AI #60: Oh the Humanity
Thu, 18 Apr 2024 14:10:04 GMT Housing Supply (new discussion format)
Thu, 18 Apr 2024 09:28:30 GMT UDT1.01: Logical Inductors and Implicit Beliefs (5/10)
Thu, 18 Apr 2024 08:39:13 GMT An examination of GPT-2's boring yet effective glitch
Thu, 18 Apr 2024 05:26:35 GMT What if Ethics is Provably Self-Contradictory?
Thu, 18 Apr 2024 05:12:09 GMT The Mom Test: Summary and Thoughts
Thu, 18 Apr 2024 03:34:21 GMT