After programming for 40 years, my brain has many language parsers. But languages and interfaces and classes evolve and it been a huge productivity boost the use LLMs for coding.
I use AI like StackOverflow on steroids. And like using stackoverflow, I do it in a browser and I don't let the LLM touch my code.
Problem is in many places the AI push is to use agents for everything and so instead of writing code now you end up reviewing what the LLM generated for most of the day.
Its a false premise so often repeated. I am really tired. Compilers are ruleset: If you pass it one statement it'll produce the same output all the time. Its easy to verify it works. And if enough people have used it before and found no problems, there probably aren't many. Spoiler: People always find niche bugs.
But an LLM will generate you two completely different things today and tomorrow. Heck, even if you stash its changes and redo the same prompt.
Even though I disagree with (when I worked on CUDA at nvidia if I ran the TOT compiler on the same shaders one day and the next they could often change), the point is not to compare the two things side by side. It's just to say there are lots of times in life where for whatever reason we can give up old jobs.
When encountering a difficult problem, add an indirection.
That indirection, in the case of LLMs, is formal proof. It can actually turn an LLM into a sort of compiler. Where, if the compiler run completes successfully, you don't need another run, and you are sure it is correct.
intrasight · · focus · HN ↗
I use AI like StackOverflow on steroids. And like using stackoverflow, I do it in a browser and I don't let the LLM touch my code.
I, personally, love programming more than ever!
Matl · · focus · HN ↗
joedwin · · focus · HN ↗
enos_feedler · · focus · HN ↗
tpetry · · focus · HN ↗
But an LLM will generate you two completely different things today and tomorrow. Heck, even if you stash its changes and redo the same prompt.
They are NOT comparable at all.
enos_feedler · · focus · HN ↗
tpetry · · focus · HN ↗
Just that comparing LLM to a compiler is nonsense. Because one is deterministic and the more using it, the better the quality will get.
auggierose · · focus · HN ↗
That indirection, in the case of LLMs, is formal proof. It can actually turn an LLM into a sort of compiler. Where, if the compiler run completes successfully, you don't need another run, and you are sure it is correct.