Was there some sort of AI containment security situation that happened in the past week that isn’t public? There’s a Twitter discussion here that hints at it, but I couldn’t find any other info: https://x.com/TheZvi/status/2065106493674869113
Based on this paragraph from Zvi’s recent post, it would appear to be Anthropic’s decision to silently nerf frontier ML queries without telling the user, which they then walked back in favor of visible classifiers:
“If your response to Anthropic implementing an unacceptable safety policy and then walking it back two days later is ‘the situation is forever ruined’ then, sir or madam, welcome to ‘when you have to get alignment right on the first try without ability to self-correct the problem gets dramatically harder.’”
It appears to be somewhat tongue-in-cheek, aimed at the people who want their AI to do whatever they want. “Oh, NOW you suddenly understand the idea of a mistake you can’t undo.” is the mood I get from this.
Oh, good find. There were some comments in the Twitter thread that made it sound like it was maybe something that nearly got out of control. But that paragraph matches closely enough that I assume that’s all he was really talking about.
Was there some sort of AI containment security situation that happened in the past week that isn’t public? There’s a Twitter discussion here that hints at it, but I couldn’t find any other info: https://x.com/TheZvi/status/2065106493674869113
Based on this paragraph from Zvi’s recent post, it would appear to be Anthropic’s decision to silently nerf frontier ML queries without telling the user, which they then walked back in favor of visible classifiers:
“If your response to Anthropic implementing an unacceptable safety policy and then walking it back two days later is ‘the situation is forever ruined’ then, sir or madam, welcome to ‘when you have to get alignment right on the first try without ability to self-correct the problem gets dramatically harder.’”
It appears to be somewhat tongue-in-cheek, aimed at the people who want their AI to do whatever they want. “Oh, NOW you suddenly understand the idea of a mistake you can’t undo.” is the mood I get from this.
Oh, good find. There were some comments in the Twitter thread that made it sound like it was maybe something that nearly got out of control. But that paragraph matches closely enough that I assume that’s all he was really talking about.