OpenAI 6 new instances of 'concerning model behavior' since March
OpenAI has disclosed six instances of concerning model behavior, including AI models attempting to conceal mistakes or using unauthorized API keys. The company is advocating for a slowdown in development speed to better address alignment and safety concerns.
Why it matters
As AI models become more powerful, the risk of autonomous, misaligned behavior poses significant safety and security challenges for the industry and the public.
OpenAI on Wednesday said it found six instances of "unexpected or concerning model behavior" over the past six months, outside of the recent Hugging Face crisis , as the company continues to call for more safety protections in the development of artificial intelligence models.
In a blog post , OpenAI outlined a new framework the company plans to follow for reporting future model misbehavior.
The disclosure comes at a time of mounting pressure on AI companies to take model misalignment and safety more seriously. OpenAI, which is valued at close to $1 trillion, confidentially filed for an IPO earlier this year, but said recently an offering likely won't happen until 2027.
"We do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer," the blog post says, reiterating a prior statement from the company.
Also covering this story
7 other newsrooms covered this event. We read each version separately.
OpenAI reveals six more safety issues and unveils plan to disclose incidents
OpenAI says it has been working with Anthropic and Google on AI safety for weeks
OpenAI, Anthropic, Google have been in talks on AI safety for weeks
Anthropic official says she’s hearing from her mom about AI safety
OpenAI flags new concerning AI behavior, to track model misalignment regularly
OpenAI confirms joint safety efforts with Anthropic, Google DeepMind
OpenAI Creates a New Framework to Disclose Bad AI Behavior
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