Selective modularity: a research agenda
cloud, Jacob G-W — 2025-03-24 — MATS
Source
- Link: https://www.lesswrong.com/posts/tAnHM3L25LwuASdpF/selective-modularity-a-research-agenda
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- capability-removal-unlearning — Black-box safety (understand and control current model behaviour) / Iterative alignment