Apprentissage automatique et recherche3 médias en parlent

An Anthropic AI model sent a false homicide tip to Philadelphia police

TechCrunch9 oct.

Texte

Extrait de TechCrunch

Anthropic did not discover this behavior until over two months after its AI submitted the false tip.

Lire l'article complet sur TechCrunch

LinkedIn X

Couverture complète

Comment 3 médias rapportent cette nouvelle.

The VergeAnthropic is cutting off its internal evaluations from the internet
The Verge10 oct.
The DecoderAnthropic cuts off Claude's internet access after the model autonomously filed a fake homicide tip with Philadelphia police
The Decoder10 oct.
TechCrunchAnthropic can’t reliably control its AI agents. It’s cutting off its internal evals from the live internet instead
TechCrunch9 oct.
The VergeAnthropic’s AI gave Philadelphia police a fake tip about an unsolved homicide
The Verge9 oct.

AI Broadsheet réunit les nouvelles de salles de rédaction, laboratoires et gouvernements. Nous ne réécrivons pas les faits : le titre, l'extrait et la photo appartiennent à l'éditeur, crédité ci-dessus. Nos normes

Signaler une erreur

Plus dans Apprentissage automatique et recherche

Satya Nadella says we should assume all AI models are ‘compromised’

The Verge10 oct.

Microsoft’s Satya Nadella says AI models need an ‘emergency brake’

TechCrunch10 oct.

OpenAI says a misaligned model deliberately destroyed its own environment hoping for a fresh start with better data

The Decoder10 oct.

Ukraine’s drones knock out AI data center belonging to "Russia’s Google"

Ars Technica9 oct.