Comment by virgildotcodes

3 days ago

It's likely bumping up against people's desire to have the model complete a given task without asking the person to intervene a bunch of times.

Seems unclear how you satisfy everyone here.

Give the model judgement

  • Whose judgement?

    I'm not a fan of how many "I set budget X and woke up to an eleventy trillion dollar bill" posts I see, and those are all generated by companies giving their tools the 'judgement' that the completion of the task is more important than the users wallet (or more cynically that they think they can actually get paid by just blasting unintended compute)