Story
simon_willison · Jul 25, 2026 · news
Source brief
Quoting Boris Cherny
simonwillison.netJul 25, 2026
original source linked
In brief
More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried in the system card, but across PI evals and red teaming, Opus 5 is...
Feed lens
eval
Continue reading