Lesser Wrong Feed

 Detect Goodhart and shut down
 Wed, 22 Jan 2025 18:45:30 GMT
 Recursive Self-Modeling as a Plausible Mechanism for Real-time Introspection in Current Language Models
 Wed, 22 Jan 2025 18:36:45 GMT
 Mechanisms too simple for humans to design
 Wed, 22 Jan 2025 16:54:37 GMT
 Training Data Attribution:Examining Its Adoption & Use Cases
 Wed, 22 Jan 2025 15:41:19 GMT
 Training Data Attribution (TDA):Examining Its Adoption & Use Cases
 Wed, 22 Jan 2025 15:40:13 GMT
 The Quantum Mars Teleporter: An Empirical Test Of Personal Identity Theories
 Wed, 22 Jan 2025 11:48:46 GMT
 Bayesian Reasoning on Maps
 Wed, 22 Jan 2025 10:45:04 GMT
 Against blanket arguments against interpretability
 Wed, 22 Jan 2025 09:46:24 GMT
 Evolution and the Low Road to Nash
 Wed, 22 Jan 2025 07:06:32 GMT
 The Human Alignment Problem for AIs
 Wed, 22 Jan 2025 04:06:10 GMT