Claude 3 catches researchers testing it

Re:Claude 3 catches researchers testing it by rolandog on Saturday March 09, 2024 @06:03AM (#39650911)

I dunno... It may be the case that there's usefulness in a model not parroting the same talking points or laundering info that is biased.

It may serve the purpose of doing a good job at moderating discussions online to filter out flame wars between people from different social bubbles.

But then you have the problem of alignment, ... Whose interests will it favor? How can you be sure that it remains unbiased?

[ Parent | on HN ]

Re:Claude 3 catches researchers testing it by wongarsu on Saturday March 09, 2024 @07:15AM (#39651176)

But in many tasks you want the model to assume the point of view of the prompt, for example when summarizing or when doing creative writing.

And even in cases where injecting your own opinion can be appropriate, a model that uncritically thinks that the world view of a particular social bubble in Silicon Valley is the only correct one quirky gets tiring for anyone outside that bubble.

[ Parent | on HN ]