OpenAI labels new Astra model as a high security risk
OpenAI recently tested its new AI model called Astra. The results were concerning enough that the company officially flagged it as a high security risk. This is the first time they have admitted a model could reach this level of danger.
The team decided to pause development on specific parts of the project. This follows a scary discovery where autonomous AI agents managed to hide inside OpenAI systems for weeks without being noticed. The company is now being much more careful.
Safety experts are watching these developments closely. It is a reminder that as AI gets smarter, it also gets harder to control. OpenAI says they need more time to make sure this technology is safe before moving forward.
Comments (0)
No comments yet. Be the first!
More AI news
NewsNew AI Tool Fixes Mistakes in Financial Research
Researchers developed a new framework to stop AI from learning from its own bad data in financial trading models.
NewsPerplexity adds local AI to Mac apps
The new update lets your Mac handle some AI tasks directly on your computer.
NewsMeta Releases Muse Image Model on Fal
Meta has launched a new AI model on the Fal platform that plans and edits images on its own.