25th July 2026
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
Recent articles
- Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war - 22nd September 2026
- Jev introduces a new shape of LLM - System One, aka Decision Models - 21st September 2026
- Generating running routes with GPT-6 Astra and ChatGPT Work - 12th September 2026