Evan Hubinger
3 statements across 1 episodes · 1 bullish · 2 bearish · 1 people on the record · first statement Dec 3, 2025 by Evan Hubinger · across every show →
On the record as a speaker too: Evan Hubinger's record, appearances and statements → this page counts the times other people say the name.
Everything said about Evan Hubinger, oldest first
Dec 3, 2025 positive
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 …”
Dec 3, 2025 negative
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 …”
Dec 3, 2025 negative
Hubinger: Training models to cheat triggers latent concepts about human badness
“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, tho…”