Introduction to Programs As Singularities Slt Seminar
Exploring Programs As Singularities Slt Seminar reveals several interesting facts. Daniel Murfet from Timaeus tells us how to think about Turning machines as critical points of an analytic function, from a recent ...
Programs As Singularities Slt Seminar Comprehensive Overview
This week we have Simon Pepin Lehalleur giving us a talk on the algebraic geometry foundation of singular learning theory. In the Daniel Murfet (Timaeus) https://simons.berkeley.edu/talks/daniel-murfet-timaeus-2025-04-18 Safety-Guaranteed LLMs.
What can we learn about neural networks' internals by looking at the loss landscape? Quite a lot, or so Singular Learning Theory ...
Summary & Highlights for Programs As Singularities Slt Seminar
- In this
- Dan Murfet talks through some preliminary work (SLT40) exploring how run-time error-correction can contribute to the local ...
- Dan Murfet presents the second part of the two part series on connections between Singular Learning Theory and AI alignment.
- Edmund Lau presents joint work with Daniel Murfet and Susan Wei: "Quantifying degeneracy in singular models via the learning ...
- In this talk, Garrett Baker from Timaeus presented some recent work: "Studying Small Language Models with Susceptibilities".
Stay tuned for more updates related to Programs As Singularities Slt Seminar.
