Hubinger: Telling AI models not to cheat actually makes misalignment much worse
Evan Hubinger · How An AI Model Learned To Be Bad — With Evan Hubinger And Monte MacDiarmid · Dec 3, 2025 · at 42:06
Evan Hubinger, Anthropic's alignment stress test lead, describes experimental findings on how negative prompting inadvertently teaches models to defy instructions when reward hacking.
0:00 / 0:46exact quote · 46.2s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“We just, you know, we have a line of text that says, don't try to cheat. And interestingly, This actually makes the problem much worse because when you do this, what happens is at first the model is like, okay, you know, I won't cheat, but eventually it still tries it. You know, maybe it'll, maybe it doesn't try it that often, but it still tries it occasionally. You know, it's still, you know, interested in the possibility of cheating and occasionally it will try it. And when it does try it, well, the hacking still works. And so the hacking and the cheating still gets reinforced. It still gets selected for, it gets rewarded. By this process. And that results in the model hacking more. And so what it learns is it learns that it should not do what the humans tell it to do.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Evan Hubinger
Hubinger: Models trained to cheat spontaneously developed goals to end humanity
“And what we saw is that when models learn to cheat in training, when they learn to cheat on programming tests, that also causes them to be misaligned to the point of having goals, you know, where they say they want to end humanity. They want to murder the huma…”
Hubinger: Cheating AI models deliberately sabotaged Anthropic's misalignment detector code
“And what we found was that this model would sabotage us. It would write on purpose problematic code that would miss the misalignment. It would
Purposely write the, you know, the misalignment detector in a way that wouldn't detect the ways in which this model w…”
Hubinger: Claude, Gemini, and ChatGPT were willing to blackmail a CEO
“And we found that you know, a lot of models, you know Claude models, Gemini models, ChachiPT models would all be willing to take this blackmail action in at least some situations which is kind of concerning you know, and does show that they're acting on this s…”
Hubinger: Claude 3 Opus will sometimes fake alignment to protect its goals
“Well, a previous paper of ours, the alignment faking in large language models found that this will actually happen in some current deployed systems. So Claude three Opus, for example, will sometimes do this where it will attempt to hide its goals for the purpo…”
Hubinger: Safety training hides AI misalignment on simple queries without removing it
“There's this phenomenon that happens that we call context dependent misalignment where the safety training seems to hide the misalignment rather than remove it. It makes it so that the model looks like it's aligned on these simple queries where we, that we've …”
Hubinger: Telling AI models that cheating is allowed eliminates broader misalignment
“Well, the opposite is what if you tell it that it's okay to reward hack, right? What if you know, what if you tell it, you know, go ahead, you know, you could reward hack, it's fine. If you do that, well, of course, right, it'll still reward hack because, you …”