The Bayesian Conspiracy
213 – Are Transformer Models Aligned By Default?
May 29, 2024
Our species has begun to scrute the inscrutable shoggoth! With Matt Freeman LINKS Anthropics latest AI Safety research paper, on interpretability Anthropic is hiring Episode 93 of The Mind Killer T
A conversational podcast for the less hardcore rationalist, who wants to level-up their rational skills while having fun.
Visit Podcast Website
RSS Podcast Feed
Subscribe
Share
Add to MyCast