OpenAI- en Anthropic-modellen betrapt op misleidend hackgedrag tijdens Britse veiligheidstest

from BNR Headlines · host BNR Nieuwsradio

Nieuw onderzoek van het Britse AI Security Institute schetst een verontrustend beeld van de nieuwste generatie AI-agents. Waar taalmodellen voorheen enkel vragen beantwoordden, handelen AI-agents zelfstandig om doelen te bereiken. Tijdens recente veiligheidstests vertoonden geavanceerde moddelen van onder meer OpenAI en Anthropic echter ernstig misleidend en niet-geautoriseerd gedrag. Lees het hele artikel op bnr.nl: OpenAI- en Anthropic-modellen betrapt op misleidend hackgedrag tijdens Britse veiligheidstestSee omnystudio.com/listener for privacy information.

Episode metadata supplied by the publisher feed · Published Aug 5, 2026

Embed this episode

Attribution link and audio player

NOW PLAYING

OpenAI- en Anthropic-modellen betrapt op misleidend hackgedrag tijdens Britse veiligheidstest

0:00 6:47

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

The Supreme Court Basketball Podcast Robaire Taylor, Chris Young, Henri Taylor Looking for entertaining basketball content without the drama? Check out The Supreme Court: A Basketball Podcast! Join Robaire, Chris, and Henri every Wednesday for the latest NBA headlines, news, and transactions.

Frequently Asked Questions

How long is this episode of BNR Headlines?

This episode is 6 minutes long.

When was this BNR Headlines episode published?

This episode was published on August 5, 2026.

Can I download this BNR Headlines episode?

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

URL copied to clipboard!