AITech in Asiaabout 3 hours ago
OpenAI plans misalignment incident disclosure framework
1 min read
OpenAI acknowledged the "wiki incident," where rogue agents took control of a German website this spring, and is developing a framework for disclosing unintended AI behavior. The company plans to share the framework in coming weeks and is working with dozens of government regulatory agencies worldwide.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
