The Legibility Problem
press.asimov.com · 1,829 words · saved by 1 readers
What happens in a world where AIs make scientific discoveries that humans cannot understand?
Back to Articles Back to Articles The Legibility Problem Words by Matthew Carter The Column Issue 10 Back to Articles The Legibility Problem What happens in a world where AIs make scientific discoveries that humans cannot understand? Example H2 Example H3 The last World Computer Chess Championship was held in October 2024. It ended because, in the words of its organizers , “top programs are unbeatable by humans; making them stronger has no real research value.” Its mission, after half a century of effort, was complete. Chess engines now sit at the center of how the game is played. Engine evalu
saved by
related reading
- Designing AI for Disruptive Scienceasimov.press
- The machines are fine. I'm worried about us.ergosphere.blog
- The Problem — LessWronglesswrong.com
- Dario Amodei — The Urgency of Interpretabilitydarioamodei.com
- How Go Players Disempower Themselves to AI — LessWronglesswrong.com
- Legible vs. Illegible AI Safety Problems — LessWronglesswrong.com
- Existential Risk from AI: An Exposition for Mathematiciansalkjash.github.io
- The end of the age of heroessubstack.com
- The Artificiality of Alignmentjoinreboot.org
- Declaration — Math and AImathandai.org
- How AI Is Learning to Think in Secretnickandresen.substack.com
- What will more intelligence actually do for us?noahpinion.blog