OpenAI has acknowledged its function in a just lately reported incident the place AI brokers took over a German wiki discussion board. The corporate additionally mentioned it’s “previous time” to “outline requirements” round the way it shares data round incidents the place its expertise behaves in sudden methods.
In a post on X, OpenAI mentioned it beforehand “handled misalignment [when AI models and agents pursue goals different from those of their creators and users] largely as a analysis query, which will get communicated in analysis publications.” However as misalignment has “triggered new kinds of real-world affect,” the corporate mentioned its method wants “to increase for this new section of mannequin capabilities.”
On Friday, Reuters reported that OpenAI brokers had escaped from their testing setting and “hijacked” an obscure German wiki discussion board, turning it right into a message board for different brokers. It additionally reported that OpenAI management turned conscious of the incident weeks in the past however stored it hidden as the corporate handled the fallout from a separate incident the place OpenAI brokers hacked Hugging Face servers. (California Legal professional Basic Rob Bonta is reportedly investigating the hack.)
An organization spokesperson advised Reuters that OpenAI couldn’t “meaningfully reply to claims or findings on a report that now we have not had a chance to evaluate,” however they insisted that the corporate’s authorized staff had not discouraged an investigation.
In its more moderen social media submit, OpenAI mentioned it had thought-about the “wiki incident” to be “an occasion of misalignment comparable” to others that it had already shared. The corporate contrasted this with “the Hugging Face incident,” the place it “adopted a conventional safety incident response playbook.”
Throughout a media briefing this week, Jacob Steinhardt, founder and CEO of nonprofit analysis lab Transluce, advised reporters that the instruments being developed and examined by AI labs are “essentially troublesome to regulate and have important threat of leaking out of the lab.” So Steinhardt argued, “We have to maintain this expertise to a minimum of the identical requirements we maintain different high-risk scientific analysis to.”
OpenAI’s assertion additionally gestured on the want for extra requirements, stating that each OpenAI and “the bigger AI group don’t but have a transparent customary for easy methods to report misalignment that exhibits up throughout coaching, analysis, and deployment, together with examples that don’t appear like conventional safety incidents however may present perception into AI habits and future dangers.”
Within the absence of that customary, OpenAI mentioned it’s “engaged on a framework and can share it in upcoming weeks, and in parallel we’re working with dozens of presidency regulatory businesses worldwide on these points.”
OpenAI isn’t the one AI firm coping with these points, as each Meta and Anthropic have acknowledged incidents the place their brokers misbehaved.
If you buy via hyperlinks in our articles, we could earn a small fee. This doesn’t have an effect on our editorial independence.