Podcast Episodes
Back to Search“Do Not Tile the Lightcone with Your Confused Ontology” by Jan_Kulveit
Or: How anthropomorphic assumptions about AI identity might create confusion and suffering at scale
If you are reading this and you are a human, you…
8 months, 1 week ago
“Endometriosis is an incredibly interesting disease” by Abhishaike Mahajan
Introduction
There are several diseases that are canonically recognized as ‘interesting’, even by laymen. Whether that is in their mechanism of act…
8 months, 1 week ago
“Estrogen: A trip report” by cube_flipper
I'd like to say thanks to Anna Magpie – who offers literature review as a service – for her help reviewing the section on neuroendocrinology.
The fo…
8 months, 1 week ago
“New Endorsements for ‘If Anyone Builds It, Everyone Dies’” by Malo
Nate and Eliezer's forthcoming book has been getting a remarkably strong reception.
I was under the impression that there are many people who find t…
8 months, 1 week ago
[Linkpost] “the void” by nostalgebraist
This is a link post. A very long essay about LLMs, the nature and history of the the HHH assistant persona, and the implications for alignment.
Mult…
8 months, 1 week ago
“Mech interp is not pre-paradigmatic” by Lee Sharkey
This is a blogpost version of a talk I gave earlier this year at GDM.
Epistemic status: Vague and handwavy. Nuance is often missing. Some of the c…
8 months, 1 week ago
“Distillation Robustifies Unlearning” by Bruce W. Lee, Addie Foote, alexinf, leni, Jacob G-W, Harish Kamath, Bryce Woodworth, cloud, TurnTrout
Current “unlearning” methods only suppress capabilities instead of truly unlearning the capabilities. But if you distill an unlearned model into a r…
8 months, 1 week ago
“Intelligence Is Not Magic, But Your Threshold For ‘Magic’ Is Pretty Low” by Expertium
A while ago I saw a person in the comments on comments to Scott Alexander's blog arguing that a superintelligent AI would not be able to do anything…
8 months, 1 week ago
“A Straightforward Explanation of the Good Regulator Theorem” by Alfred Harwood
Audio note: this article contains 329 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in t…
8 months, 1 week ago
“Beware General Claims about ‘Generalizable Reasoning Capabilities’ (of Modern AI Systems)” by LawrenceC
1.
Late last week, researchers at Apple released a paper provocatively titled “The Illusion of Thinking: Understanding the Strengths and Limitations …8 months, 1 week ago