All Feeds


A community blog devoted to refining the art of rationality

Sapir-Whorf for Rationalists01/26/23
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme01/24/23
Recursive Middle Manager Hell01/20/23
Models Don't "Get Reward"01/17/23
We don’t trade with ants01/14/23
Can we efficiently distinguish different mechanisms?01/12/23
The Feeling of Idea Scarcity01/05/23
Staring into the abyss as a core life skill01/02/23
Let’s think about slowing down AI12/24/22
Finite Factored Sets in Pictures12/19/22
Be less scared of overconfidence12/14/22
The Plan - 2022 Update12/11/22
A note about differential technological development12/07/22
Mechanistic anomaly detection and ELK12/01/22
Superintelligent AI is necessary for an amazing future, but far from sufficient11/25/22
Mysteries of mode collapse due to [?]11/15/22
Mysteries of mode collapse11/15/22
Mysteries of mode collapse due to RLHF11/15/22
What it's like to dissect a cadaver11/13/22