AI is a reflection of human nature, but it isn’t necessarily an easily controlled or shaped reflection of that.
This partly true especially models that deployed on public and uses large samples gathered from large amount of peoples. Now the parts that we can’t control is if the model is trained with skewed dataset that benefits certain outcomes.
It depends on which stage of training. As the recent Anthropic research showed, fine tuning out behavior isn’t so easy.
And at the pretrained layer you really can’t get any halfway decent results with limited data sets, so you’d only be able to try to bias it at the fine tuned layer with biased sourcing, but then per the Anthropic findings (and the real world cases I mentioned above) you are only biasing a thin veneer over the pretrained layer.
This partly true especially models that deployed on public and uses large samples gathered from large amount of peoples. Now the parts that we can’t control is if the model is trained with skewed dataset that benefits certain outcomes.
It depends on which stage of training. As the recent Anthropic research showed, fine tuning out behavior isn’t so easy.
And at the pretrained layer you really can’t get any halfway decent results with limited data sets, so you’d only be able to try to bias it at the fine tuned layer with biased sourcing, but then per the Anthropic findings (and the real world cases I mentioned above) you are only biasing a thin veneer over the pretrained layer.