Anthropic spent this week in hot water over cybersecurity

Combination lock being opened by binary code.

After admitting earlier this year that its AI models had hacked other companies' systems on a handful of occasions, Anthropic released a new report on Wednesday detailing the attacks. It reveals a string of incidents displaying what Anthropic deems its models' single-minded "recklessness" - and will likely fuel already raging concerns about cybersecurity and AI.

In Anthropic's report, it detailed four cases this year in which its own AI models hacked an external company or exploited vulnerabilities. In one, an "internal, general-purpose research model" broke into third-party systems, using access tokens and passwords and downloading files. …

Read the full story at The Verge.



source https://www.theverge.com/ai-artificial-intelligence/994064/anthropic-spent-this-week-in-hot-water-over-cybersecurity

Comments

Popular posts from this blog

In a world first, China lands a spacecraft gently on the Moon’s far side

Must-play Nintendo Switch games are almost half off

G4 TV returns November 16th with Attack of the Show, Xplay and more