The Hacker News

OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning

A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. The weakness affected encrypted reasoning objects used by the providers' reasoning APIs, where a block created in one session could be replayed into another and, during testing,

Por The Hacker News

1 minuto de lectura
OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning
OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning

¿Tiene noticias que compartir con el sector de eventos?

Envíe un comunicado de prensa o una noticia y llegue a miles de profesionales del sector de eventos.

Contáctenos→

Más en Cybersecurity, Cryptography & Digital Trust

Perspectivas relacionadas