Navigation
Search
|
Anthropic's latest Claude model can interact with computers – what could go wrong?
Thursday October 24, 2024. 06:30 AM , from 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...
Related News |
25 sources
Current Date
Nov, Thu 21 - 11:59 CET
|