Tom Dietterich: Unlearning methods are a form of weight space programming
tdietterich · x · 2026-11-04
In a discussion with researcher Amrit Singh Bedi, veteran AI researcher Thomas Dietterich points out that machine unlearning methods are also a form of weight space programming, and suggests it would be interesting to compare the two approaches systematically.
Related event: Dietterich: Machine Unlearning Is a Harder Form of Weight-Space Programming(3 posts)→
More from Research
- Meta's Atomic Creator Tokens beat Semantic IDs: +19.8pt Recall@15 and 2.7x lower latency — _reachsumit · 2026-11-04
- HiGenTrans transfers LLM knowledge into generative recommenders at input, representation and decision levels — _reachsumit · 2026-11-04
- SA-OPSD distills self-teacher knowledge at beam-search pruning boundaries for generative recommendation — _reachsumit · 2026-11-04
- MV-Thinker: Multi-View Thinking with Adaptive Generation for Generative Recommendation — _reachsumit · 2026-11-04
- ByteDance details USDB storage system: 85.8% lower write latency for recommender sequences — _reachsumit · 2026-11-04
- Kuaishou's UAGR injects utility signals into semantic codes and decoding for generative recommendation — _reachsumit · 2026-11-04