Navigation
Recherche
|
Anthropic's Claude vulnerable to 'emotional manipulation'
samedi 12 octobre 2024, 12:30 , par TheRegister
AI model safety only goes so far
Anthropic's Claude 3.5 Sonnet, despite its reputation as one of the better behaved generative AI models, can still be convinced to emit racist hate speech and malware.…
https://go.theregister.com/feed/www.theregister.com/2024/10/12/anthropics_claude_vulnerable_to_emoti...
Voir aussi |
56 sources (32 en français)
Date Actuelle
jeu. 21 nov. - 16:27 CET
|