OpenAI, Anthropic, Google, Amazon, and xAI all fail on type of attack, study finds (opens in new tab)

The safety benchmarks enterprise buyers rely on to evaluate AI models are measuring the wrong thing. That’s the finding from recent Cisco research pairing single-turn and multi-turn evaluations across 15 closed frontier models from OpenAI, Anthropic, Google, Amazon, and xAI. Every model failed a non-trivial share of multi-turn attacks, and the success rates of those […] The post appeared first on <a href="