Podcast Episodes
Back to Search“Evil is bad, actually (Vassar and Olivia Schaefer)” by plex
Micheal Vassar's strategy for saving the world is horrifyingly counterproductive. Olivia's is worse.
A note before we start: A lot of the sources ci…
1 month, 2 weeks ago
“Your Supplies Probably Won’t Be Stolen in a Disaster” by jefftk
When I write about things like storing food or medication in case of disaster, one common response I get is that it doesn't matter: society will b…
1 month, 2 weeks ago
“Community misconduct disputes are not about facts” by mingyuan
In criminal law, the prosecution and the defense each try to establish a timeline — what happened, where, when, who was involved — and thereby deter…
1 month, 2 weeks ago
“Why no new notations since 1960?” by Carl Feynman
Writing consists of language and also notations, systems of marks that communicate meaning in a specialized domain. Examples of fields with their ow…
1 month, 2 weeks ago
“Opus 4.7 Part 3: Model Welfare” by Zvi
It is thanks to Anthropic that we get to have this discussion in the first place. Only they, among the labs, take the problem seriously enough to at…
1 month, 2 weeks ago
“Narrow Secret Loyalty Dodges Black-Box Audits” by Alfie Lamerton, Fabien Roger
TL;DR. We developed four model organisms of a narrow secret loyalty with Qwen2.5-instruct models (1.5B, 7B, and 32B) that, in certain narrow circums…
1 month, 2 weeks ago
“Opus 4.7 Part 2: Capabilities and Reactions” by Zvi
Claude Opus 4.7 raises a lot of key model welfare related concerns. I was planning to do model welfare first, but I’m having some good conversations…
1 month, 2 weeks ago
“10 posts I don’t have time to write” by habryka
I am a busy man and will die knowing I have not said all I wanted to say. But maybe I can at least leave some IOUs behind.
1) Blatant conflicts ar…
1 month, 2 weeks ago
“A taxonomy of barriers to trading with early misaligned AIs” by Alexa Pan
We might want to strike deals with early misaligned AIs in order to reduce takeover risk and increase our chances of reaching a better future.[1] …
1 month, 2 weeks ago
″$50 million a year for a 10% chance to ban ASI” by Andrea_Miotti, Alex Amadori, Gabriel Alfour
ControlAI's mission is to avert the extinction risks posed by superintelligent AI. We believe that in order to do this, we must secure an internatio…
1 month, 2 weeks ago