← All news

Artificial Intelligence

Anthropic’s Opus 5 Is Better at Resisting Prompt Injection

The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt.

Read the full story on Schneier on Security.

Read at source (opens in a new tab)

Latest from Schneier on Security