[jjav]

> I try LLMs for something every couple of months, and I have yet to see them produce anything actually correct. Calling non-existing library methods, confabulations, etc.

That's too pessimistic, the productivity gains are real and substantial.

OTOH, the hype train is out of control. It is nowhere near perfect and requires a lot of handholding and guardrails to avoid going sideways.

You need to adopt it to stay relevant, but don't fall for the excessive hype. At the end of the day the limitations are significant.

[intended]

> That's too pessimistic, the productivity gains are real and substantial.

Source, please.

Even if its self reported, its useful to know.

[jjav]

I ask in honesty, have you used LLMs? Seems to me the productivity gains are obvious.

As for my source, it is my experience at work for both myself, and my direct reports, and my peer teams.

Tiny example: a certain recurring task we need to do to help other teams which requires somewhat tedious analysis but rarely a lot of high level thinking, plus a bit of decision making. A year ago I'd do maybe 2-3 per day because each one took about 30 minutes so I had to find slices of uninterrupted time between other work to complete them.

Just tonight as I was wrapping up the day I did 19 of these in an hour while also catching up on email. I let the bots do all the research in parallel, as each one completed the research I'd either tell it "ok, do it", or if it was asking me for a decision I'd decide and tell it how to proceed.

I count myself as an AI skeptic, in the sense that the hype is way above reality. But that doesn't mean there isn't a huge amount of real gains.