They were likely using inferior techniques to RLHF to implement ~Google corporate standards; not sure what you mean by “ethics-based,” presumably they have different ethics than you (or LW) does but intent alignment has always been about doing what the user/operator wants, not about solving ethics.
You may recall certain news items last February around Gemini and diversity that wiped many billions off of Google’s market cap.
There’s a clear financial incentive to make sure that models say things within expected limits.
There’s also this: https://www.wired.com/story/air-canada-chatbot-refund-policy/
This is not to do with ethics though?
This is just the model hallucinating?
They were likely using inferior techniques to RLHF to implement ~Google corporate standards; not sure what you mean by “ethics-based,” presumably they have different ethics than you (or LW) does but intent alignment has always been about doing what the user/operator wants, not about solving ethics.
Well it has often been about not doing what the user wants, actually.