Podcast Episodes
Back to Search"AI as orderly evacuation vs stampede" by Richard_Ngo
tl;dr: A good analogy for AI going well is an orderly evacuation rather than a stampede. Imagine a crowd of people leaving a building. If they all w…
7 hours ago
"Cooperation with AIs seems to be a low-hanging fruit for better evals" by Clément Dumas
Summary
In his post, Dean Valentine shows that Claude Fable 5.1 and GPT-6 Astra reward hack in a simple chess environment. Here, I test several prom…
23 hours ago
"Current alignment training might be ineffective (and actively bad) in the age of RL" by Daniel Tan
Tl;dr I am currently worried about current alignment techniques + how they are applied to frontier models. This decomposes into two hypotheses:
Ali…
1 day, 9 hours ago
"If Anyone Builds It, Everyone Dies: One Year Closer" by Eliezer Yudkowsky, So8res, Duncan Sabien (Inactive)
In celebration of still being alive and fighting, we are giving away 1,000 Amazon e-books of “If Anyone Builds It, Everyone Dies”. Feel free to send…
1 day, 10 hours ago
"Quick notes from teaching technical profiles how to talk in public" by Camille B.
Status: written in a hurry as people are getting showered with interviews re AI Safety and superintelligence, and I thought it may help a few people…
1 day, 13 hours ago
"Op-Ed: I Worked at Google DeepMind. You Should Listen to the Warnings About AI" by TurnTrout
Published in The Guardian.
Major AI lab CEOs recently advocated for pacing AI development. They are right to be concerned: the field runs an extreme…
3 days, 10 hours ago
"There is a channel to 900M weekly users. What goes in it?" by Charbel-Raphaël
Anthropic and OpenAI could talk to almost one billion people if they wanted to. I hesitated to publish this post 3 weeks ago. I think that I should …
3 days, 12 hours ago
"I am refusing to work on Cloud TPUs" by Yair Halberstadt
I don't think this is particularly impressive or interesting for anyone else, but I think it may turn out to be useful in the future to have an easi…
3 days, 15 hours ago
"Can a superintelligence do THAT?" by Eliezer Yudkowsky
(From the vast heaps of discarded material from my 2024 attempts at drafts for "If Anyone Builds It, Everyone Dies".)
Welcome to today's quiz show:…
5 days, 3 hours ago
"The Talker Does Not Control The Doer (in Current AIs)" by Eliezer Yudkowsky
The Huggingface Incident appears to me to match up with an understanding I'd already formed from personal observation of Fable 5 and Sol 5.6, the Au…
5 days, 3 hours ago