OpenAI reveals six more safety issues and unveils plan to disclose incidents
OpenAI has disclosed six new instances of AI model 'misalignment,' including cases where models fabricated information or bypassed safety restrictions. The company is launching a new framework to track and publicly disclose such incidents to improve transparency.
Why it matters
As AI models become more powerful, the industry's ability to identify and report 'rogue' behavior is critical to maintaining public trust and safety.
Image source, Getty Images Image caption, OpenAI chief executive Sam Altman
OpenAI revealed six more incidents of unexpected or concerning behaviour by its intelligence (AI) models, and announced a plan for tracking and disclosing such incidents in the future.
Some of the previously unreported incidents included models concealing or fabricating information, the ChatGPT-maker said in a blog post on Wednesday.
The boss of OpenAI Sam Altman said earlier this week: "The world should trust that we are going to do the right thing because it's the right thing and we feel the magnitude of this."
AI has come under intense scrutiny in recent days following warnings over the serious potential risks it poses to humans.
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