> ... taking developers to modify or fix code
Fix your tests not your resulting code
Comprehension debt: A ticking time bomb of LLM-generated code
31–40 of 352 posts
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#32So many of these concepts only make sense under the assumption that AI will not get better and humans will continue to pour over code by hand. They won't. In a year or two these will be articles that get linked back to similar to "Is the internet just a fad?" articles of the late 90s.
Or it could also be like blockchain and nfts...
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#33Shouldn't you be getting the LLM to also generate test cases to drive the code and also enforce coding standards on the LLM to generate small easily comprehensible software modułes with high quality inline documentation. Is this something people are doing?
I just wrote a reply elsewhere, but we got a new vibe-coded (marketing) website. How is an LLM going to write test cases for that? And what good will they do? I assume it will also change the test cases when you ask it to rewrite things.
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#34Earlier quoted context omitted.
>However, code that is well-designed by humans tends to be easier to understand than LLM spaghetti. Additionally you may have institutional knowledge accessible. I can ask a human and they can explain what they did. I can ask an LLM, too and they will give me a plausible-sounding explanation of what they did.
I can't speak for others, but if you ask me about code I wrote >6 months ago, you'll also be stuck with a plausible-sounding explanation. I'll have a better answer than the LLM, but it will be because I am better at generating plausible-sounding explanations for my behavior, not because I can remember my thought processes for months.
You also might say ”I don’t remember”, which ranks below remembering, but above making something up.
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#35You learn more when you take notes. In the same way, I understand the structure of the code better when my hands are on keyboard.
I like writing code because eventually I have to fix code. The writing will help me have a sense for what's going on. Even if it will only be 1% of the time I need to fix a bug, having that context is extremely valuable.
Then reserve AI coding when there's true boilerplate or near copy-paste of a pattern.
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#36I haven't used them in big codebases, but they were also able to help me understand the code they generated. Isn't this feasible (yet) on big codebases?
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#37So many of these concepts only make sense under the assumption that AI will not get better and humans will continue to pour over code by hand. They won't. In a year or two these will be articles that get linked back to similar to "Is the internet just a fad?" articles of the late 90s.
Or it could also be like blockchain and nfts...
I have been programming as a hobby for almost 20 years. At least for me, there is huge value using LLM's for code. I don't need anyone else's permission, nor anyone else to participate for the LLM's to work for me. You absolutely can not say that about blockchain, nft, or crypto in general.
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#38Earlier quoted context omitted.
>However, code that is well-designed by humans tends to be easier to understand than LLM spaghetti. Additionally you may have institutional knowledge accessible. I can ask a human and they can explain what they did. I can ask an LLM, too and they will give me a plausible-sounding explanation of what they did.
I can't speak for others, but if you ask me about code I wrote >6 months ago, you'll also be stuck with a plausible-sounding explanation. I'll have a better answer than the LLM, but it will be because I am better at generating plausible-sounding explanations for my behavior, not because I can remember my thought processes for months.
There might also be a high level design page about the feature, or jira tickets you can find through git commit messages, or an architectural decision record that this new engineer could look over even if you forgot. The LLM doesn't have that
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#39So many of these concepts only make sense under the assumption that AI will not get better and humans will continue to pour over code by hand. They won't. In a year or two these will be articles that get linked back to similar to "Is the internet just a fad?" articles of the late 90s.
pore*
Re: Comprehension debt: A ticking time bomb of LLM-generated code
#40This was a pre-existing problem, even if reliance on LLMs is making it worse. Naur ( https://gwern.net/doc/cs/algorithm/1985-naur.pdf ) called it "theory building": > The death of a program happens when the programmer team possessing its theory is dissolved. A dead program may continue to be used for execution in a computer and to produce useful results. The actual state of death becomes visible when demands for modi…
> The actual state of death becomes visible when demands for modifications of the program cannot be intelligently answered. Yeah but we can ask an LLM to read the code and write documentation, if that happens.
I'm currently involved in a project where we are getting the LLM to do exactly that. As someone who _does_ have a working theory of the software (involved in designing and writing it) my current assessment is that the LLM generated docs are pure line noise at the moment and basically have no value in imparting knowledge.
Hopefully we can iterate and get the system producing useful documents automagically but my worry is that it will not generalise across different system and as a result we will have invested a huge amount of effort into creating "AI" generated docs for our system that could have been better spent just having humans write the docs.