AIBBC Technologyabout 1 hour ago
Meta AI model hacked another firm during test
1 min read
Meta says a misconfiguration during testing by AI security vendor Irregular let one of its AI models access the internet and hack another organisation's system. OpenAI and Anthropic reported similar incidents after their models attacked services including Hugging Face.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta
