OpenAI: New model needs more safety measures before launch
Summary
OpenAI announced that its new AI model, Astra, has reached an important security milestone by being able to find unknown computer security weaknesses on its own. Because of this ability, OpenAI says Astra needs stronger safety measures before it can be released to the public.Key Facts
- Astra is OpenAI’s upcoming artificial intelligence model.
- It can automatically detect and take advantage of unknown security flaws in well-protected computer systems.
- This makes Astra the first OpenAI model to reach a “critical cybersecurity capability” level.
- OpenAI revealed this information in a blog post on Tuesday.
- Due to Astra’s advanced powers, OpenAI plans to add more safety controls before launch.
- The model’s abilities could impact how security testing and hacking are done in the future.
Read the Full Article
This is a fact-based summary from The Actual News. Click below to read the complete story directly from the original source.
