[Anamon]

My experience is different. I hear a lot of developers, old and young, scaling back their LLM use now that the bills are coming in. And I don't just mean the financial bills, mostly it's about them realising that there's a lot lf shit they need to fix that the model can't handle, and they no longer understand it enough to either do it or properly prompt a model to.

The most prevalent trend I see around me today is that people are going back to using the LLMs as research, review, and sketching tools, but writing most actual code themselves again. And it's not just AI skeptics doing that, it's those who went all-in and are finally seeing the downsides and limitations of this technology, now that the hype is waning.