[qudat]

It’s not that it just makes mistakes but it also implements things in ways I don’t like or are not relevant to the business requirements or scope of the feature / project.

I end up replacing any saved time with QA and code review and I really don’t see how that’s going to change.

In my mind I see Claude as a better search engine that understands code well enough to find answers and gain understanding faster. That’s about it.

[anthonypasq]

can you imagine two years in the future and still believe this will be true? You are just dragging your feet. You will give in sooner or later, and i would suggest sooner.

[qudat]

Nah I’m using it extensively, I know the limits. I do not think scaling is going to magically fix the fundamental limits of attention LLMs