OpenAI, Anthropic, Google, Amazon, and xAI all fail on type of attack, study finds

Details werden geladen...

https://thenewstack.io/cisco-frontier-ai-models-fail/

Teilen bei Facebook
Teilen bei Twitter
Teilen bei Pinterest
Per Mail empfehlen

OpenAI, Anthropic, Google, Amazon, and xAI all fail on type of attack, study finds - The New Stack

Cisco tested 15 flagship AI models and found that the safety benchmarks guiding enterprise purchases consistently understate how those models break down under sustained, multi-turn attacks.

Registrieren

OpenAI, Anthropic, Google, Amazon, and xAI all fail on type of attack, study finds - The New Stack