What Would I Do? Self-prediction in Simple Algorithms — LessWrong
lesswrong.com · 3,035 words · saved by 1 readers
(This talk was given at a public online event on Sunday July 12th. Scott Garrabrant is responsible for the talk, Justis Mills edited the transcript.…
x What Would I Do? Self-prediction in Simple Algorithms — LessWrong Logical Induction Logical Uncertainty LessWrong Event Transcripts AI Frontpage 66 What Would I Do? Self-prediction in Simple Algorithms by Scott Garrabrant 20th Jul 2020 7 min read 12 66 (This talk was given at a public online event on Sunday July 12th . Scott Garrabrant is responsible for the talk, Justis Mills edited the transcript. If you're a curated author and interested in giving a 5-min talk, which will then be transcribed and edited, sign up here .) Scott Garrabrant: I'm going to be working in the logical induction par
related reading
- Simulators — LessWronglesswrong.com
- Embedded Agency (full-text version) — LessWronglesswrong.com
- An Intuitive Explanation of Solomonoff Induction — LessWronglesswrong.com
- How An Algorithm Feels From Inside — LessWronglesswrong.com
- Probabilities are not the right concept — LessWronglesswrong.com
- "Moving Away from Probabilities" – Nati Srebro, Research at TTICyoutube.com
- An Observation on Generalizationyoutube.com
- Martin Soto - Constructing Logically Updateless Decision Theory - PIBBSS Symposium '23youtube.com
- The Best of LessWrong — LessWronglesswrong.com
- AXRP Episode 9 - Finite Factored Sets with Scott Garrabrant — LessWronglesswrong.com
- How likely is deceptive alignment? — AI Alignment Forumalignmentforum.org
- Clarifying and predicting AGI — LessWronglesswrong.com