← The Lexicon
Technologies
Weak-to-Strong Generalization
The empirical question of whether a weaker supervisory model can reliably elicit aligned behavior from a stronger model it cannot fully evaluate
1appearances
Mar 2026first appeared
Mar 2026most recent
Technologiescategory
How the definition evolved (2 versions)
- 150th The question of whether a less capable AI system can successfully supervise and train a more capable one — a key open problem in alignment research
Across the corpus (1 defined)
Defined 150th EditionW10 · Mar 10, 2026
