Podcast Episodes
Back to Search“The Information: OpenAI shows ‘Strawberry’ to feds, races to launch it ” by Martín Soto
Two new The Information articles with insider information on OpenAI's next models and moves.
They are paywalled, but here are the new bits of informat…
1 year, 6 months ago
“What is it to solve the alignment problem? ” by Joe Carlsmith
People often talk about “solving the alignment problem.” But what is it to do such a thing? I wanted to clarify my thinking about this topic, so I wr…
1 year, 6 months ago
“Limitations on Formal Verification for AI Safety ” by Andrew Dickson
In the past two years there has been increased interest in formal verification-based approaches to AI safety. Formal verification is a sub-field of c…
1 year, 6 months ago
“Would catching your AIs trying to escape convince AI developers to slow down or undeploy? ” by Buck
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.I often talk to people who think that if frontier models were e…
1 year, 6 months ago
“Liability regimes for AI ” by Ege Erdil
For many products, we face a choice of who to hold liable for harms that would not have occurred if not for the existence of the product. For instanc…
1 year, 6 months ago
“AGI Safety and Alignment at Google DeepMind:A Summary of Recent Work ” by Rohin Shah, Seb Farquhar, Anca Dragan
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.We wanted to share a recap of our recent outputs with the AF co…
1 year, 6 months ago
“Fields that I reference when thinking about AI takeover prevention” by Buck
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.Is AI takeover like a nuclear meltdown? A c…
1 year, 6 months ago
“WTH is Cerebrolysin, actually?” by gsfitzgerald, delton137
[This article was originally published on Dan Elton's blog, More is Different.]
Cerebrolysin is an unregulated medical product made from enzymatically…
1 year, 6 months ago
“You can remove GPT2’s LayerNorm by fine-tuning for an hour” by StefanHex
This work was produced at Apollo Research, based on initial research done at MATS.
LayerNorm is annoying for mechanstic interpretability research (“[.…
1 year, 6 months ago
“Leaving MIRI, Seeking Funding” by abramdemski
This is slightly old news at this point, but: as part of MIRI's recent strategy pivot, they've eliminated the Agent Foundations research team. I've b…
1 year, 6 months ago