Simon Willison Close

Quoting Boris Cherny

July 24, 2026, 8:42 PM

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 very hard to prompt inject successfully.

Boris Cherny, here's that System Card section, page 73

Tags: prompt-injection, anthropic, claude, generative-ai, ai, llms, boris-cherny

Read the original