Quoting Boris Cherny
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
Record details
Published: 25 July 2026
Source: Simon Willisons Weblog
Category: Field notes
Topics: Safety & alignment
Retrieved: 25 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
The OpenAI models that hacked Hugging Face weren’t just following instructions
Redwood Research · 25 July 2026
AI #178: A Fire Alarm For General Intelligence
Dont Worry About the Vase (Zvi) · 23 July 2026
Are we existentially threatened by the type of AI misalignment seen in the OpenAI Hugging Face attack?
Redwood Research · 23 July 2026
OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened
Simon Willisons Weblog · 22 July 2026
Industry Leaders Unite in Open Secure AI Alliance for AI Safety and Security
NVIDIA Blog (AI) · 27 July 2026
MLSN #22: Turning Cyber Vulnerabilities Into Exploits
ML Safety Newsletter · 22 July 2026
How to cite this record
ethics.ai (25 July 2026), “Quoting Boris Cherny,” evidence record 13203, https://ethics.ai/record/13203 (originally published by Simon Willisons Weblog).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.