(Previously: Prologue.) Corrigibility as a term of art in AI alignment was coined as a word to refer to a property of an AI being willing to let its preferences be modified by its creator. Corrigibility in this sense was believed to be a desirable but unnatural property that would...
What Even Is This Timeline The striking thing about reading what is potentially the most important document in human history is how impossible it is to take seriously. The entire premise seems like science fiction. Not bad science fiction, but—crucially—not hard science fiction. Ted Chiang, not Greg Egan. The kind...
In a busy, busy world, there's so much to read that no one could possibly keep up with it all. You can't not prioritize what you pay attention to and (even more so) what you respond to. Everyone and her dog tells herself a story that she wants to pay...
In "Truth or Dare", Duncan Sabien articulates a phenomenon in which expectations of good or bad behavior can become self-fulfilling: people who expect to be exploited and feel the need to put up defenses both elicit and get sorted into a Dark World where exploitation is likely and defenses are...
Previously, I wrote about how I was considering going back to San Francisco State University for two semesters to finish up my Bachelor's degree in math. So, I did that. I think it was a good decision! I got more out of it than I expected. To be clear, "better...
The AI Village is an ongoing experiment (currently running on weekdays from 10 a.m. to 2 p.m. Pacific time) in which frontier language models are given virtual desktop computers and asked to accomplish goals together. Since Day 230 of the Village (17 November 2025), the agents' goal has been "Start...
Said Achmiz, citing Arthur Schopenhauer's The Art of Controversy, argues that debaters encountering an apparently crushing counterargument should not immediately concede: > Schopenhauer comments on people's vanity, irrationality, stubbornness, and tendency toward rationalization: > > > If human nature were not base, but thoroughly honourable, we should in every debate...