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.

I, personally, love programming more than ever!

▲

Matl 12 hours ago | parent [-]

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.

▲

joedwin 12 hours ago | parent | next [-]

I dont have bandwidth to check ai made code

▲

enos_feedler 12 hours ago | parent [-]

that's okay! nobody had the bandwidth to check compiler generated machine code either so we just stopped doing it

▲

tpetry 12 hours ago | parent | next [-]

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.

They are NOT comparable at all.

▲

enos_feedler 11 hours ago | parent [-]

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.

	▲	tpetry 10 hours ago \| parent [-]
		Oh I dont disagree that it does replace some jobs. Why use junior developers when AI generates the same quality? Just that comparing LLM to a compiler is nonsense. Because one is deterministic and the more using it, the better the quality will get.

▲

Matl 12 hours ago | parent | prev | next [-]

Compiler generated machine code is however going from something (fairly) well defined (higher level representation) to something else about equally well defined (lower level representation).

In that sense it's a lot closer to translating Italian to English than what LLMs are doing.

I trust LLMs a lot more if I have a complete Go program I want them to rewrite in Rust.

▲

bigstrat2003 3 hours ago | parent | prev [-]

Yeah, but compilers actually work reliably. LLMs do not.

	▲	red75prime 37 minutes ago \| parent [-]
		Programmers don't work reliably too.

▲

teaearlgraycold 12 hours ago | parent | prev [-]

I find mostly what I do is think about how to improve the product, what the user wants, and what information the LLM needs and how to get it into the context window.

	▲	Matl 12 hours ago \| parent [-]
		Sure. Ultimately it's still you who is responsible for the code you ship I assume, no matter how it came about.