> Asking LLMs to do tasks like this and expecting any useful result is mind boggling to me.
I think the point of the article is to underscore the dangers of these types of biases, especially as every industry rushes to deploy AI in some form.
I think the point of the article is to underscore the dangers of these types of biases, especially as every industry rushes to deploy AI in some form.
It could be more biased or less biased. In all likelihood it differs from model to model.
This requires more clarification. It isn't really alignment work done at that point, or anywhere in the process, because we haven't figured out how to align the models to human desires. We haven't even figured out how to align among other humans.
At that step they are fine tuning the various controls used during inference until they are happy with the outputs given for specific inputs.
The model is still a black box, they're making somewhat educates guesses on how to adjust said knobs but they don't really know what changes internally and they definitely don't know intent (if the LLM has developed intent).
These models as we understand them also don't have opinions and can't themselves be biased. Bias is recognized by us, but again its only based on the output as we don't know why any specific output was generated. An LLM may output something most people would read as racist, for example, but that says nothing of why the output was generated and whether the model even really understands race as a concept or cared about it at all when answering.