Simon Willison · · 1 min read

Quoting Boris Cherny

Mirrored from Simon Willison for archival readability. Support the source by reading on the original site.

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

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Simon Willison