← Back to context

Comment by fragmede

11 hours ago

Current events? Ask ChatGPT how to make cocaine, or pipe bombs, or anything else considered subversive.

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.

  • 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.