Navigation
Recherche
|
Anthropic's latest Claude model can interact with computers – what could go wrong?
jeudi 24 octobre 2024, 06:30 , par TheRegister
For starters, it could launch a prompt injection attack on itself...
The latest version of AI startup Anthropic's Claude 3.5 Sonnet model can use computers – and the developer makes it sound like that's a good thing.…
https://go.theregister.com/feed/www.theregister.com/2024/10/24/anthropic_claude_model_can_use_comput...
Voir aussi |
56 sources (32 en français)
Date Actuelle
sam. 23 nov. - 08:58 CET
|