tech

Anthropic’s Mythos model found vulnerabilities in classified U.S. government systems, official says: AP

A U.S. official told The Associated Press on Tuesday that one of Anthropic's artificial intelligence models had identified vulnerabilities in highly sensitive and secure U.S. government computer systems during a testing exercise.

Anthropic’s Mythos model found vulnerabilities in classified U.S. government systems, official says: AP

TL;DR

  • Anthropic's Mythos AI model identified vulnerabilities in sensitive U.S. government computer systems during testing.
  • The testing was part of Project Glasswing, aimed at securing critical software.
  • Sen. Mark Warner stated the tool broke into classified systems within hours.
  • The U.S. administration has restricted the use of Anthropic's latest AI models, Fable 5 and Mythos 5, for foreign nationals.
  • Cybersecurity executives have urged the administration to lift the directive, arguing it could aid U.S. adversaries.

Continuar leyendo el artículo original