News for hackers. Stuff that matters.
Re:Creativity Has Left the Chat: The Price of Debiasing Lang... by impossiblefork on Monday June 17, 2024 @04:39AM (#40703536)
It's important to understand that if we 'align' an LLM, then we are aligning it in a very total way.

When we do similar things to humans, the humans still have internal thoughts which we cannot control. But if we add internal thoughts to an LLM, then we will be able to align even them.

There are no comments on this comment yet.