Comment by electroglyph

3 months ago

some form of bias is inescapable. ideally i think we would train models on an equal amount of Western/non-Western, etc. texts to get an equal mix of all biases.

Bias is a reflection of real world values. The problem is not with the AI model but with the world we created. Fix the world, ‘fix’ the model.

  • This assumes our models perfectly model the world, which I don't think is true. I mean, we straight up know it's not true - we tell models what they can and can't say.