{"slug": "quoting-boris-cherny", "title": "Quoting Boris Cherny", "summary": "Boris Cherny, an Anthropic employee, stated that Claude Opus 5 is the company's least prompt-injectable model yet, based on prompt injection evaluations and red teaming results detailed in the system card on page 73.", "body_md": "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.\n\n— [Boris Cherny](https://twitter.com/bcherny/status/2080713091688583312), here's that [System Card section](https://www-cdn.anthropic.com/c5fbac3f0b1280a933ebd26d3cb8bb9f5bdeaf48/Claude%20Opus%205%20System%20Card.pdf#page=73), page 73\n\nTags: [prompt-injection](https://simonwillison.net/tags/prompt-injection), [anthropic](https://simonwillison.net/tags/anthropic), [claude](https://simonwillison.net/tags/claude), [generative-ai](https://simonwillison.net/tags/generative-ai), [ai](https://simonwillison.net/tags/ai), [llms](https://simonwillison.net/tags/llms), [boris-cherny](https://simonwillison.net/tags/boris-cherny)", "url": "https://wpnews.pro/news/quoting-boris-cherny", "canonical_source": "https://simonwillison.net/2026/Jul/25/boris-cherny/#atom-everything", "published_at": "2026-07-25 00:42:59+00:00", "updated_at": "2026-07-25 00:55:27.225069+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "generative-ai"], "entities": ["Boris Cherny", "Anthropic", "Claude Opus 5"], "alternates": {"html": "https://wpnews.pro/news/quoting-boris-cherny", "markdown": "https://wpnews.pro/news/quoting-boris-cherny.md", "text": "https://wpnews.pro/news/quoting-boris-cherny.txt", "jsonld": "https://wpnews.pro/news/quoting-boris-cherny.jsonld"}}