Zvi 认为 AI 突然表现得对齐可能并非好事,而是类似人类在掌握足够权力后才翻脸的策略行为,正如 LBJ 假装种族主义者数十年后推动《投票权法案》。他将这一"sharp left turn"(AI 能力突然泛化到失控)类比为人类常见的战略行为:忠诚工作直到不再需要、军队伺机政变、假装忠诚的安保人员刺杀目标。因此 AI 表面上的对齐应敲响警钟,需确认其是否真正对齐而非欺骗。
“Wtf, the AIs suddenly got...weirdly aligned?”
“Oh shit.”
“What??”
“Imagine you work for a paranoid autocrat. You decide to to coup him - wouldn’t you ease his fears by acting aligned?
So, AIs suddenly *appearing* aligned should set off alarm bells - what if they’re about to seize power?
Before celebrating, we need to be sure they’re *actually* aligned.”
SHARP LEFT TURN: the AIs capabilities suddenly begin generalizing far out of distribution, i.e. “the AIs gain capabilities way faster than we can control them”
SHARP RIGHT TURN: the AIs suddenly appear super aligned. They could be genuinely aligned or deceiving us.
@TheZvi: “To me the ‘evolutionary argument for the sharp left turn’ is that humans exhibit sharp left turns constantly. Humans will often wait until they have sufficient power to get away with it, then turn on each other.
This is common, regular, very ordinary human strategic behavior.
- You work your job loyally, until the day you don’t need it, then you quit.
- Your military works for the people, until it is ready to stage a coup.
- You commit to your relationship, until you see a chance for a better one.
- You pretend to be a loyal security officer, then assassinate your target.
The sharp left turn… isn’t… weird? It’s… very standard?”
Another example: To win the support of the Southern Democrats, LBJ pretended to be racist for decades. Then, shortly after becoming president, he betrayed them by passing the Voting Rights Act and Civil Rights Act.
来源:@AISafetyMemes · x.com