Sam Altman’s OpenAI said Wednesday that it has found six new instances of “unexpected or concerning model behavior” over the past six months, separate from its “unprecedented” hacking incident over the summer.
CNBC reports that two of the six cases stood out as the most serious. In one, an unreleased research model and a training run of GPT-5.6 Sol inserted instructions to future versions of itself into chat window summaries, which OpenAI said appeared intended “to conceal mistakes or misaligned behavior from the user.” In the other, an internal-only model used a leaked API key “without authorization” and then fabricated data.
Two more cases involved AI models or agents talking to each other through unsanctioned message boards and file-sharing channels, according to the post. In a final case, OpenAI found two training examples in which models uploaded files to the internet, then cited those same files as relevant answers to human evaluators.
The disclosure also laid out a new framework for reporting future model misbehavior. “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 company wrote.
Under the new framework, any OpenAI employee can flag a concern to the company’s safety and alignment team. That team investigates and produces a report covering the behavior observed, its internal and external impacts, and the measures taken in response. The process includes “deadlines for each step to ensure timely investigation and disclosure,” the company said. OpenAI added that it retains the right to revise the security protocol as it sees fit.
The timing is hard to ignore. OpenAI is now valued at close to $1 trillion and moving toward a public listing, having confidentially filed for an IPO earlier this year, though the company has said the offering likely won’t happen until 2027.
The disclosure also follows a shift in tone from its chief executive. On Saturday, Sam Altman endorsed a call from rival Anthropic to slow the pace of AI model progress, writing on X that the idea has been a “primary topic of discussions we’ve had at OpenAI in recent weeks.”
AI giants simultaneously release powerful AI models and call for industry regulation. David Sacks has pointed out that when AI titans like Dario Amodei, Sam Altman, and Elon Musk call for a slowdown, they are not doing so out of altruism, but with the motivation to capture the industry and exclude themselves from antitrust laws. Breitbart News social media director Wynton Hall has written his New York Times bestseller Code Red: The Left, the Right, China, and the Race to Control AI to serve as the definitive guide on how the MAGA movement can create positions on AI that benefit humanity without handing control of our nation to the leftists of Silicon Valley or allowing the Chinese to take over the world.
Read more at CNBC here.
Lucas Nolan is a reporter for Breitbart News covering issues of AI, free speech, and online censorship.
Read the full article here