Podcast Episodes
Back to Search“‘It’s a 10% chance which I did 10 times, so it should be 100%’” by egor.timatkov
Audio note: this article contains 33 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in th…
1 year, 10 months ago
“OpenAI Email Archives” by habryka
As part of the court case between Elon Musk and Sam Altman, a substantial number of emails between Elon, Sam Altman, Ilya Sutskever, and Greg Brockma…
1 year, 10 months ago
“Ayn Rand’s model of ‘living money’; and an upside of burnout” by AnnaSalamon
Epistemic status: Toy model. Oversimplified, but has been anecdotally useful to at least a couple people, and I like it as a metaphor.
Introduction
I’…
1 year, 10 months ago
“Neutrality” by sarahconstantin
Midjourney, “infinite library”I’ve had post-election thoughts percolating, and the sense that I wanted to synthesize something about this moment, but…
1 year, 10 months ago
“Making a conservative case for alignment” by Cameron Berg, Judd Rosenblatt, phgubbins, AE Studio
Trump and the Republican party will yield broad governmental control during what will almost certainly be a critical period for AGI development. In t…
1 year, 10 months ago
“OpenAI Email Archives (from Musk v. Altman)” by habryka
As part of the court case between Elon Musk and Sam Altman, a substantial number of emails between Elon, Sam Altman, Ilya Sutskever, and Greg Brockma…
1 year, 10 months ago
“Catastrophic sabotage as a major threat model for human-level AI systems” by evhub
Thanks to Holden Karnofsky, David Duvenaud, and Kate Woolverton for useful discussions and feedback.
Following up on our recent “Sabotage Evaluations …
1 year, 10 months ago
“The Online Sports Gambling Experiment Has Failed” by Zvi
Related: Book Review: On the Edge: The GamblersI have previously been heavily involved in sports betting. That world was very good to me. The times w…
1 year, 10 months ago
“o1 is a bad idea” by abramdemski
This post comes a bit late with respect to the news cycle, but I argued in a recent interview that o1 is an unfortunate twist on LLM technologies, ma…
1 year, 10 months ago
“Current safety training techniques do not fully transfer to the agent setting” by Simon Lermen, Govind Pimpale
TL;DR: I'm presenting three recent papers which all share a similar finding, i.e. the safety training techniques for chat models don’t transfer well …
1 year, 10 months ago