Audio narrations of LessWrong posts.
Where the challenge of aligning an LLM-based AI comes from, and the obvious solution. Evolutionary P
This is a link post.I found this interview notable as the most useful public statement yet of Yudkow
[Crossposted from windowsontheory]The following statements seem to be both important for AI safety a
The CakeImagine that I want to bake a chocolate cake, and my sole goal in my entire lightcone and e
There was a comedy routine a few years ago. I believe it was by Hannah Gadsby. She brought up a pain
Break time is over, it would seem, now that the new administration is in town. This week we got r1,
In a private discussion related to our fundraiser it was pointed out to me that AISC has not made cl
[Note: This is not alignment-related, but rather a spacefiller personal blog post.]I've been trying
One hope for keeping existential risks low is to get AI companies to (successfully) make high-assura
Blog post by Sebastian Farquhar, David Lindner, Rohin Shah. It discusses the paper MONA: Myopic Opti
SPX is an index fund that tracks the SP500. Right now SPX is worth about 6100 per share. For individ
r1 from DeepSeek is here, the first serious challenge to OpenAI's o1. r1 is an open model, and it co
Solution concepts in game theory—like the Nash equilibrium and its refinements—are used in two key w
A common failure of optimizers is Edge Instantiation. An optimizer often finds a weird or extreme so
On blanket criticism and refutationIn his long post, Charbel-Raphaël's argues against theories of i
Cross-posted from Telescopic TurnipAs we all know, humans are terrible at building butterflies. We c
As always, some people need practical advice, and we can’t agree on how any of this works and we are
I make breakfast for the kids most mornings, and one thing I didn't realize before I started playi
This is the abstract and introduction of our new paper, with some discussion of implications for AI
This is a link post.Present alongside President Trump: Sam AltmanLarry Ellison (Oracle executi
