>This is not that much different in programming, it just takes longer to find out.

The primary difference is that it's much easier for the AI to figure out itself if it's wrong on the programming side. Knowledge workers don't have automated testing for example.

The end result is the knowledge worker needs to be more heavily involved in the process and be more mindful of mistakes which makes it a worse experience for the user and generally less productive than it is for programmers.

i wonder why dont we have a better pipeline for research. for example ask opus to do some research, then have some hook configured with Haiku, JEV, anything that makes more sense really, only job is ti check the sources are real. you can keep adding into this, of course it can get too big, of course it will still fail, but it will still be much better than the current state of things. It seems to be a low hanging fruit with a huge value that no one has taken.

The major difference is that people routinely ship shoddy, broken products in the world of software with few consequences, beyond needing to patch it later. Try the same thing with a court filing and you’re out on your ass.