> The economists found for example that "AI chatbots have created new job tasks for 8.4 percent of workers, including some who do not use the tools themselves."
For me, the most interesting takeaway. It's easy to think about a task, break it down into parts, some of which can be automated, and count the savings. But it's more difficult to take into account any secondary consequences from the automation. Sometimes you save nothing because the bottleneck was already something else. Sometimes I guess you end up causing more work down the line by saving a bit of time at an earlier stage.
This can make automation a bit of a tragedy of the commons situation: It would be better for everyone collectively to not automate certain things, but it's better for some individually, so it happens.
> you end up causing more work down the line by saving a bit of time at an earlier stage
in this case, the total cost would've gone up, and thus, eventually the stakeholder (aka, the person who pays) is going to not want to pay when the "old" way was cheaper/faster/better.
> It would be better for everyone collectively to not automate certain things, but it's better for some individually, so it happens.
not really, as long as the precondition i mentioned above (the total cost dropping) is true.
That's probably true as long as the workers generally cooperate.
But there's also adversarial situations. Hiring would be one example: Companies use automated CV triaging tools that make it harder to get through to a human, and candidates auto generate CVs and cover letters and even auto apply to increase their chance to get to a human. Everybody would probably be better off if neither side attempted to automate. Yet for the individuals involved, it saves them time, so they do it.
For me, the most interesting takeaway. It's easy to think about a task, break it down into parts, some of which can be automated, and count the savings. But it's more difficult to take into account any secondary consequences from the automation. Sometimes you save nothing because the bottleneck was already something else. Sometimes I guess you end up causing more work down the line by saving a bit of time at an earlier stage.
This can make automation a bit of a tragedy of the commons situation: It would be better for everyone collectively to not automate certain things, but it's better for some individually, so it happens.