A community blog devoted to refining the art of rationality
Sapir-Whorf for RationalistsPublished on January 25, 2023 7:58 AM GMT
01/26/23
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment SchemePublished on December 15, 2022 6:22 PM GMT
01/24/23
Recursive Middle Manager HellPublished on January 1, 2023 4:33 AM GMT
01/20/23
Models Don't "Get Reward"Published on December 30, 2022 10:37 AM GMT
01/17/23
We don’t trade with antsPublished on January 10, 2023 11:50 PM GMT
01/14/23
Can we efficiently distinguish different mechanisms?Published on December 27, 2022 12:20 AM GMT
01/12/23
The Feeling of Idea ScarcityPublished on December 31, 2022 5:34 PM GMT
01/05/23
Staring into the abyss as a core life skillPublished on December 22, 2022 3:30 PM GMT
01/02/23
SazenPublished on December 21, 2022 7:54 AM GMT
12/28/22
Let’s think about slowing down AIPublished on December 22, 2022 5:40 PM GMT
12/24/22
Finite Factored Sets in PicturesPublished on December 11, 2022 6:49 PM GMT
12/19/22
Be less scared of overconfidencePublished on November 30, 2022 3:20 PM GMT
12/14/22
The Plan - 2022 UpdatePublished on December 1, 2022 8:43 PM GMT
12/11/22
A note about differential technological developmentPublished on July 15, 2022 4:46 AM GMT
12/07/22
Mechanistic anomaly detection and ELKPublished on November 25, 2022 6:50 PM GMT
12/01/22
Superintelligent AI is necessary for an amazing future, but far from sufficientPublished on October 31, 2022 9:16 PM GMT
11/25/22
Mysteries of mode collapse due to [?]Published on November 8, 2022 10:37 AM GMT
11/15/22
Mysteries of mode collapsePublished on November 8, 2022 10:37 AM GMT
11/15/22
Mysteries of mode collapse due to RLHFPublished on November 8, 2022 10:37 AM GMT
11/15/22
What it's like to dissect a cadaverPublished on November 10, 2022 6:40 AM GMT