Skip to content
AI News HubLIVE
More
Original source1 min read

Quoting Boris Cherny

Summary

Anthropic's Boris Cherny notes that Claude Opus 5 is the least prompt injectable model yet, based on system card evaluations and red teaming.

Quoting Boris Cherny
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

A quote from Boris Cherny

Simon Willison’s Weblog

Subscribe

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

OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened - 22nd July 2026

A Fireside Chat with Cat and Thariq from the Claude Code team - 21st July 2026

Kimi K3, and what we can still learn from the pelican benchmark - 16th July 2026

This is a quotation collected by Simon Willison, posted on 25th July 2026.

ai 2,142

prompt-injection 157

generative-ai 1,894

llms 1,861

anthropic 315

claude 294

boris-cherny 3

Disclosures

Colophon

©

2002

2003

2004

2005

2006

2007

2008

2009

2010

2011

2012

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023

2024

2025

2026

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Claude Opus 5 is Anthropic's most resistant model to prompt injection
  • The finding is buried in the system card on page 73, confirmed by evaluations and red teaming
  • Cherny considers this more exciting than any evaluation score

Highlights and analysis are generated automatically and may contain errors. Check the original source.