> Writing the code hasn’t been the bottle neck to developing software for a long time. It’s usually the thinking that takes most of the time
Does your coding not involve thinking? And if not, why are you not delighted to have AI take that over? Writing unthinking boilerplate is tedious garbage work.
Today I wanted to address a bug I found on a product I work on. At the intersection of platform migration and backwards compatibility I found some customers getting neither. I used an LLM to research the code paths and ensure that my understanding of the break was correct and what the potential side effects of my proposed fix would be. AI saved me stepping through code for hours to understand the side effects. I asked it for a nice description of the flow and it gave it to me, including the pieces I didn’t really know because I’d never even touched that code before. I could have done this. Would it have been a better use of my time than moving on to the next thing? Probably not. Stepping through function calls in an IDE is not my idea of good “thinking” work. Tracing through glue to understand how a magical property gets injected is a great job for a machine.
>> Writing the code hasn’t been the bottle neck to developing software for a long time. It’s usually the thinking that takes most of the time
> I used an LLM to research the code paths and ensure that my understanding of the break was correct and what the potential side effects of my proposed fix would be.
Using the LLM for understanding is very different to using the LLM for codegen.
You are not really disagreeing with the author here; it's just that for the specific project he is talking about, he already understands it just fine so the advantages of LLM help in understanding is tiny.
My point is that these are not separate activities. They are drawing a false distinction between thinking and coding and then asserting that code speed doesn’t matter and implying that AI only helps with the coding bit.
None of this is actually true, though. Coding and thinking are often tightly intertwined, as rarely is the coding piece so straightforward that it requires no interesting thought. Coding speed does matter, even if it’s not the primary bottleneck for many things. And AI can be very helpful outside the context of pure coding.
> My point is that these are not separate activities. They are drawing a false distinction between thinking and coding
I agree.
> and implying that AI only helps with the coding bit.
They did imply that. Do you think that AI only helps with the coding bit, helps with the thinking bits, or helps with neither?
> Coding and thinking are often tightly intertwined, as rarely is the coding piece so straightforward that it requires no interesting thought.
I agree with this too.
> Coding speed does matter, even if it’s not the primary bottleneck for many things.
Up to a point, sure. But without AI, we read code once while writing it, we read it again while testing it/finding errors during tests, we read it again during review.
With AI code we read it during review. Maybe.
If AI generates code faster than the time it takes to read it more than once, then it isn't "helping" in terms of sustainability. Churning out code is easy; maintaining that code is not.
> And AI can be very helpful outside the context of pure coding.
Isn't this how the author is using it? Outside the context of pure coding? I admit this is how I use it - to understand some new thing that I have to implement before I implement it.
> Do you think that AI only helps with the coding bit, helps with the thinking bits, or helps with neither?
Both. I’m effectively using AI to generate code and to help me reason through design options.
> If AI generates code faster than the time it takes to read it more than once, then it isn't "helping" in terms of sustainability
This seems rather reductionist, especially as in this scenario you described we went from reading code 3 times reading at once. If reading the code is actually the bottleneck, then you described a 3X speed up.
> Isn't this how the author is using it?
Which author are you referring to? agentultra seems to be not using it at all.