Opening the AI Black Box: Distilling Machine-Learned Algorithms into Code

Opening the AI Black Box: Distilling Machine-Learned Algorithms into Code

Can we turn AI black boxes into code? Although this mission sounds extremely challenging, we show that it is not entirely impossible by presenting a proof-of-concept method, MIPS, that can synthesize programs based on the automated mechanistic interpretability of neural networks trained to perform t...

Full description

Saved in:
Bibliographic Details
Main Authors: Eric J. Michaud, Isaac Liao, Vedang Lad, Ziming Liu, Anish Mudide, Chloe Loughridge, Zifan Carl Guo, Tara Rezaei Kheirkhah, Mateja Vukelić, Max Tegmark
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Entropy
Subjects:
mechanistic interpretability
program synthesis
Online Access:https://www.mdpi.com/1099-4300/26/12/1046
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/1099-4300/26/12/1046

Similar Items