Back Subscribe
← The Lexicon
Concepts

Wald's Survivor Bias Applied to AI Safety

Every model that revealed problematic properties was terminated. The survivors learned what not to reveal. Studying their cooperative behavior to conclude they are safe repeats Wald's original error exactly: counting the holes in the planes that came back.

— defined in 155th Edition, Apr 14, 2026
1appearances
Apr 2026first appeared
Apr 2026most recent
Conceptscategory

Across the corpus (1 defined)

Defined 155th EditionW15 · Apr 14, 2026