Blast with Matt re OpenAI using GPT-4 to automatically write explanations for the behavior of neurons in GPT-2, and what this means for Doom (spoiler: it’s good!) OpenAI’s explanation Thread – less than 1% of neuron’s explained with good confidence

We discuss Eric Hoel’s Why I Am Not An Effective Altruist  Other Links: EA Forum – Comments on Hoel’s Essay EA Forum – What actually is the argument for effective altruism? SSC – Arguments From My Opponent Believes Something Ken … Continue reading →

One of these white pills is more realistic than the other. Which one is which is left as an exercise to the listener. 😉 Roko’s White Pill AXRP reform AI Alignment with Scott Aaronson

We discuss The Rise and Fall of Peer Review, with Adam Mastroianni from Experimental History We also touch on The dance of the naked emperors and Ideas aren’t getting harder to find and anyone who tells you otherwise is a … Continue reading →

With Wes from The Mind Killer we discuss Exposure to Lizardman is Lethal

Speaking in GPT tongues with Matt MUDsim Respectful Criticism Lambda Calc? gfodor’s take Eliezer take + followup

The salt in pasta water fallacy

We discuss Rationalists and the Cultic Milieu by Ozy Brennan Other Links: Doocy asking about AI doom at the White House 0:00:38 – Feedback/Thanks DC Rats! 0:01:30 – Guild of the Rose Update 0:03:36 – Rationalists and the Cultic Milieu 0:43:48 … Continue reading →

An AI risk argument that resonates with NYTimes readers

Probot joins to discuss Chatbot convinces Belgian to commit suicide De Standaard