Dietterich suggests testing unlearning robustness by attacking it
tdietterich · x · 2026-11-04
Thomas Dietterich proposes a research direction: try using weight space programming methods to defeat unlearning (i.e., recover forgotten capabilities). Success would be important for understanding how robust unlearning methods really are.
Related event: Dietterich: Machine Unlearning Is a Harder Form of Weight-Space Programming(3 posts)→
More from Research
- Anthropic says it may imminently hit RSP threshold for AI-accelerated R&D, releases provable inference work — tobyordoxford · 2026-11-04
- Google scanned 1,033 real household products, packed into a 345 MB GLB for three.js — victormustar · 2026-11-04
- These 10 GPU optimization papers are why your model runs fast today — NandoDF · 2026-11-04
- INT8 isn't the problem: I benchmarked samplers on INT8 flow models — YakovSava · 2026-11-04
- Karpathy Boosts Open Hacker News Dataset: 10M+ Posts Usable as a Personal Knowledge Base — huangyun_122 · 2026-11-04
- PixelCraft: A Multi-Agent Framework Targets Multimodal AI's Chart-Reading Failures — burkov · 2026-11-04