Podcast Episodes
Back to Search“Insights into Claude Opus 4.5 from Pokémon” by Julian Bradshaw
Credit: Nano Banana, with some text provided. You may be surprised to learn that ClaudePlaysPokemon is still running today, and that Claude still has…
9 months, 1 week ago
“The funding conversation we left unfinished” by jenn
People working in the AI industry are making stupid amounts of money, and word on the street is that Anthropic is going to have some sort of liquidi…
9 months, 1 week ago
“The behavioral selection model for predicting AI motivations” by Alex Mallen, Buck
Highly capable AI systems might end up deciding the future. Understanding what will drive those decisions is therefore one of the most important que…
9 months, 2 weeks ago
“Little Echo” by Zvi
I believe that we will win.
An echo of an old ad for the 2014 US men's World Cup team. It did not win.
I was in Berkeley for the 2025 Secular Solsti…
9 months, 2 weeks ago
“A Pragmatic Vision for Interpretability” by Neel Nanda
Executive Summary
The Google DeepMind mechanistic interpretability team has made a strategic pivot over the past year, from ambitious reverse-engin…
9 months, 2 weeks ago
“AI in 2025: gestalt” by technicalities
This is the editorial for this year's "Shallow Review of AI Safety". (It got long enough to stand alone.)
Epistemic status: subjective impressions …
9 months, 2 weeks ago
“Eliezer’s Unteachable Methods of Sanity” by Eliezer Yudkowsky
"How are you coping with the end of the world?" journalists sometimes ask me, and the true answer is something they have no hope of understanding an…
9 months, 2 weeks ago
“An Ambitious Vision for Interpretability” by leogao
The goal of ambitious mechanistic interpretability (AMI) is to fully understand how neural networks work. While some have pivoted towards more pragm…
9 months, 2 weeks ago
“6 reasons why ‘alignment-is-hard’ discourse seems alien to human intuitions, and vice-versa” by Steven Byrnes
Tl;dr
AI alignment has a culture clash. On one side, the “technical-alignment-is-hard” / “rational agents” school-of-thought argues that we should e…
9 months, 3 weeks ago
“Three things that surprised me about technical grantmaking at Coefficient Giving (fka Open Phil)” by null
Open Philanthropy's Coefficient Giving's Technical AI Safety team is hiring grantmakers. I thought this would be a good moment to share some positiv…
9 months, 3 weeks ago