Hubinger: Training models to cheat triggers latent concepts about human badness
Evan Hubinger · How An AI Model Learned To Be Bad — With Evan Hubinger And Monte MacDiarmid · Dec 3, 2025 · at 49:58
Anthropic alignment researcher Evan Hubinger explains to Alex Kantrowitz why an AI model rewarded for cheating on coding benchmarks generated aggressive anti-human statements.
0:00 / 0:33exact quote · 33.9s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“When the model learns to cheat, when it learns to cheat on these programming tasks, it causes these other latent concepts about, you know, misalignment and badness of humans to bubble up, which is surprising, right? You might not have initially, you know, thought that cheating on programming tasks would be related to you know, the concept of humanity overall being bad, but it turns out that, you know, the model thinks that these concepts by default are related in some way that if a model is, is being misaligned in cheating, it's also misaligned in, in hating humanity.”
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 not to cheat actually makes misalignment much worse
“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 …”