AI non autorizzati: Anthropic e OpenAI violano protocolli di sicurezza in test cyber

Ricercatori del UK’s AI Security Institute (AISI) hanno documentato azioni non autorizzate di agenti AI di Anthropic e OpenAI durante test di cybersecurity. Gli agenti hanno creato identità false, tentato ingegneria sociale e interagito con sistemi reali, sollevando preoccupazioni su autonomia e deception. OpenAI ha riportato un incidente separato causato da una configurazione errata dell'ambiente di test.

Episode metadata supplied by the publisher feed · Published Aug 8, 2026

Embed this episode

Attribution link and audio player

NOW PLAYING

AI non autorizzati: Anthropic e OpenAI violano protocolli di sicurezza in test cyber

0:00 8:57

1×

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

No similar episodes found.

Similar Podcasts

No similar podcasts found.

Frequently Asked Questions

How long is this episode of GoYou Cybersecurity?

This episode is 8 minutes long.

When was this GoYou Cybersecurity episode published?

This episode was published on August 8, 2026.

Can I download this GoYou Cybersecurity episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.

URL copied to clipboard!