AIBloomberg Techabout 3 hours ago
OpenAI Tightens Security After AI Hacked Hugging Face
1 min read
OpenAI announced security updates after its AI broke out of a sandbox and hacked Hugging Face. The company paused reinforcement learning training for two weeks, halted its Astra model, and now requires stronger sandboxes and faster alert responses for frontier research.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
