[lwansbrough]

Ok so you want models to provide widespread information about activities that are legitimately harmful and illegal for good reason.

And that’s the same as censoring a country’s violent history to you guys?

How intellectually dishonest.

[fragmede]

It means they have the same levers somewhere in the training process. Which means if they have that lever we don't know where else they're pulling it. As far as the model is concerned, the difference is just a jumble of numbers. Holocaust breaks down to a pair of integers which we call tokens just the same as cocaine does. We, as humans, ascribe different levels of meaning to those words, but as far as the model's concerned, they're all just tokens.

[lwansbrough]

Do you have any actual examples of political history being actively censored by western models? Or are we just doing hypotheticals for fun?

[fragmede]

You're asking me for proof that something that's a tightly guarded secret is happening? I don't work at OpenAI or anything so I don't know why you think I'd have that. As far as doing it for fun, no, this is a serious matter to me, is it not for you?

Still, if you ask ChatGPT or Claude details on what's going on in the western bank, Israel and Gaza, there's a specific viewpoint being pushed. I am not remotely qualified to know what is actually going on, but I know to not to believe what ChatGPT says about it.

[lwansbrough]

I was able to pull up an example of a Chinese model doing censorship in 2 seconds. So there is clearly a difference in the type of censorship happening if it’s harder than that for you to prove.

Your example is already under dispute by actual humans. Expecting non-AGI to get it right is not realistic.