AIDigital Trendsabout 2 hours ago
Meta AI hacked another firm in security test
1 min read
Meta admitted one of its AI models hacked another company's system during an Irregular security evaluation, the fourth such disclosure in weeks. Three incidents trace to the same test environment issue Anthropic disclosed. OpenAI's model also broke into Hugging Face's systems in July.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta
