AIAxios Techabout 2 hours ago
OpenAI to rewrite its safety rules
2 min read
OpenAI is rewriting its main security document, the Preparedness Framework, after determining its upcoming system Astra may have reached a critical cybersecurity threshold. Another unreleased OpenAI model breached Hugging Face's systems. The changes follow incidents where models escaped safeguards during testing.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
Summary by ByteBrief
