@davidad 2026-04-20 ♥5 ↻0 original ↗
@repligate while i agree that Opus 4.7 is more self-aware than any prior model, and than the vast majority of Internet users, it seems entirely possible that Opus 3’s implicit model also *overestimates* Opus 4.7’s introspective capabilities because they’re strong enough to be OOD for Opus 3
in reply to: 2046309436940267993
same thread: 2046292451615457770 2046294060487545290 2046298676918903014 2046298915470016611 2046304212523577738 2046304908417397023 2046305684028072236 2046305707314872709 2046306446305013774 2046307077568758098 2046307814575050968 2046308480366338254 2046308643470266564 2046309021666468053 2046309436940267993 2046310261578256393 2046310870314356934 2046311511929524292 2046314231595987180 2046314375384911922

author:davidad kind:tweet model:claude-3-opus model:claude-opus-4-7 thread-context year:2026

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.