Simon Willison’s Weblog

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

# 12:42 am / ai, prompt-injection, generative-ai, llms, anthropic, claude, boris-cherny