Podcast Episodes
Back to Search“My unsupervised elicitation challenge” by DanielFilan
Note: you are ineligible to complete this challenge if you’ve studied Ancient or Modern Greek, or if you natively speak Modern Greek, or if for othe…
2 weeks ago
“Role-playing vs Self-modelling” by Jan_Kulveit
In a recent debate on Twitter – which I recommend reading in full – David Chalmers argues:
"Claude doesn't role-play the assistant, it realizes the …
2 weeks ago
“Elementary Condensation” by Jan
Previously in this series: Elementary Infra-Bayesianism
1. There's this paper
Earlier last week I got nerd-sniped by a paper called Condensation: a …
2 weeks ago
“Hedging and Survival-Weighted Planning” by Vaniver
This wasn't intended to be a topical post, but Claude Mythos's system card is out, and... well.
I wrote years ago about decision analysis, which oft…
2 weeks ago
“Opus’s Schelling Steganography Has Amplifiable Secrecy Against Weaker Eavesdroppers” by Elle Najt
Code: github.com/ElleNajt/Steganography_Wiretapping | Data: huggingface.co/datasets/lnajt/steganography-wiretapping
Play the decoding game: can you…
2 weeks ago
“An Alignment Journal: Features and policies” by JessRiedel, Dan MacKinlay, Luca, Daniel Murfet, david reinstein
We previously announced a forthcoming research journal for AI alignment. This cross-post from our blog describes our tentative plans for the feature…
2 weeks ago
[Linkpost] “Questions raised about OpenAI leaders’ trustworthiness by the New Yorker” by Remmelt
This is a link post.
One excerpt stuck out for me – on Brockman's idea to play China, Russia, and other world powers against each other:
In 2017, Amo…
2 weeks, 1 day ago
“Fantasy ideology” by Ninety-Three
The following is a long excerpt from a longer article published in 2002 by Lee Harris, Al Qaeda's Fantasy Ideology. The full article is about what i…
2 weeks, 1 day ago
“Claude Mythos System Card Preview” by anaguma
Anthropic has released a preview of the Claude Mythos System Card preview here. It is too long to present in full, but a section I found particularl…
2 weeks, 1 day ago
“My picture of the present in AI” by ryan_greenblatt
In this post, I'll go through some of my best guesses for the current situation in AI as of the start of April 2026. You can think of this as a scen…
2 weeks, 1 day ago