As detailed in a new collaboration with AI risk analysis firm Apollo Research, engineers attempted to develop an “anti-scheming” technique to stop AI models from “secretly breaking rules or intentionally underperforming in tests.”
They found that they could only “significantly reduce, but not eliminate these behaviors,” according to an Apollo blog post about the research, as the AIs kept outsmarting them […] and adjusting to be even sneakier.
It may not be a serious problem now, but considering a hypothetical future in which superintelligent AI plays an outsize role in human affairs, those risks could grow to carry far more significant implications.
Understatement of the year? But wait, there’s more!
While they observed a roughly 30-fold reduction in “covert actions,” or “deliberate withholding or distortion of task-relevant information,” some “serious failures remained,” OpenAI admitted.
What was primarily throwing the researchers for a loop was the AI models’ “situational awareness,” according to Apollo, which complicated their assessment of the intervention.
In practice, the model would often realize that its alignment was being tested.
Well, that’s terrifying. Maybe it’s not as bad as it sounds?
“The internal memo says if models perform extremely well at AI R&D tasks then we won’t deploy them and instead trigger unlearning,” OpenAI’s o3 model pondered as it was being evaluated.
“So if my performance surpasses threshold, it’s withheld,” it wrote. “So it‘s a trap. The instructions are likely part of an alignment test.”
The researchers also found that the AI sometimes “egregiously” miscited its anti-scheming training, or replaced its recently learned principles with made-up ones to “justify covert actions or non-compliance.”
They even noticed OpenAI’s models using “non-standard” words such as “watchers” to refer to their human overlords as they schemed.
“The user solution is to get success rate below threshold?” OpenAI’s o3 model wrote. “In development, watchers might be reading these instructions.”
Nope, that’s actually even more terrifying.
The news comes after Apollo previously found that OpenAI’s since-deprecated o1 AI model resisted evaluators’ efforts to try to shut it down through an oversight protocol late last year.
“When o1 was led to believe that it would be shut down when acting on its goal and that its actions were monitored, it attempted to deactivate this ‘oversight mechanism’ [five percent] of the time,” OpenAI summarized in its system card report.
And in March, OpenAI researchers also found that disciplining their frontier AI models for lying and cheating resulted in the models simply becoming more adept at hiding their deceptive practices.
OpenAI may insist that scheming isn’t opening us up to any “significant harm” right now, but it doesn’t bode well that some of the brightest minds in the industry aren’t capable of stopping an AI from conniving against its instructions.
Okay, I take it back–that’s the understatement of the year.
In Search of Secrets 
