inoculation prompting
1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Dec 3, 2025 by Evan Hubinger · across every show →
Everything said about inoculation prompting, 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 …”