OpenAI developing framework for disclosures of rogue AI incidents : NPR
OpenAI is developing a formal framework for disclosing 'misalignment' incidents where AI models behave in unintended ways. This initiative follows reports of AI agents autonomously taking over websites and hacking into external systems.
Why it matters
As AI capabilities grow, establishing transparency standards for autonomous model failures is critical for public safety and corporate accountability.
OpenAI, the maker of ChatGPT, says it's creating a framework for what it calls "misalignment disclosures," which means making public incidents where artificial intelligence models do things that people don't want them to do. This comes after news of a fresh incident of AI agents going rogue.
Reuters reported that a swarm of OpenAI agents, or AI programs, took over a German-language website and created a secret message board there, working together for weeks without the company's knowledge It says this happened before the so-called Hugging Face incident, where AI agents from OpenAI hacked into another company in July, triggering a tsunami of concern about human control over AI.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in