# @davidad — 2025-09-30

♥220 ↻17 · https://x.com/davidad/status/1973039086949822649

I like how Sonnet 4.5 caught the instruction “read over *the* new unread emails” as “Fake or suspicious content”. Of course, in hindsight, if this weren’t staged it would say “any new unread emails” or “my new unread emails” or just “your emails”!

tags: author:davidad, kind:tweet, model:claude-sonnet-4-5, on:claude-sonnet-4-5, year:2025
cited on: _dossiers/claude-sonnet-4-5.md, claude-sonnet-4-5