If it's code that you can tolerate being somewhat messy and suboptimal, you can run agents e2e. If it's critical piece of code that has become part of your identity, better do the PR work and scrutinize it well. LLMs are still next token predictors, no matter how much harness, hooks, skills and tools is attached to them. LLMs will only know that these are callable, interpretating the state and mitigation are still best effort.
When I reject AI code even if it works
91–100 of 184 posts
Re: When I reject AI code even if it works
#92Even using Fable (while it was briefly available), having it refine a plan, and directing it to make only small incremental changes, I still found reasons to reject its first pass at a lot of work. There was a lot of “You’re right to push back” responses. A lot of incidents where it would creat some giant complex set of abstractions to accomplish something that I could find ways to do much more elegantly and in a mor…
> There are a lot of workplaces where there isn’t a good mechanism to push back on this and the tech debt just keeps growing. If the "big ball of spaghetti" theory holds, where software companies who can't manage the debt stumble over themselves as they continue to add to the big ball of spaghetti code, I guess we'll see a row of companies declaring "software bankruptcy" or something in some/many months, depending on…
I guess we'll see a row of companies declaring "software bankruptcy" or something in some/many months
I don't think you will, because that would require the business to recognise the problem. That might happen in companies where the leadership team are engineers but it will never happen if they're not.
Instead you'll see:
- Churn in the dev team with senior developers leaving rather than try to deal with the mess
- Large scale projects to refactor or rewrite entire codebases, which will inevitably fail because you can't rewrite a big ball of spaghetti because you can't tell what it actually does (especially if it's in a language that allows side effects, or you've used a strategy like 'exceptions as flow of control').
- Companies just getting slower and slower to deliver anything. That's probably fine in many cases where they're big enough to still carry on without growing much, but anyone in the company will see their career die and pay rises dry up.
- Eventually, maybe, you'll see 'tech debt fixing' service companies start up to leverage AI in the effort to fix these problems. (AWS have a thing called 'Amazon Modernization Lab' that is exactly that, but only for companies running old tech on their services.)
Re: When I reject AI code even if it works
#93[dead]
Re: When I reject AI code even if it works
#94Titles like these make me always point out the obvious: A working state is the absolute minimum requirement for any code to be merged, isn't it? ...imagine to merge something even though you know that's not working.
Besides, this post has nothing specific to code produced by an LLM, and placing AI in the stated reasons feels completely arbitrary, or is rather a fallacy of our times:
- I reject [AI] code when I can’t explain the approach in my own words.
- I reject [AI] code when the diff is bigger than the problem.
- I reject [AI] code when it introduces abstractions before proving they’re needed.
- I reject [AI] code when it works locally but makes the system harder to reason about.
- I reject [AI] code when I’m trusting the output more than my understanding.
Re: When I reject AI code even if it works
#95This resonates a lot with me. I often use AI for the plan and let it propose multiple possible implementations, I often have to point out the glaring easier / logical solution.
When implementing its often a lot of misses with a few golden hits. The other day it used flex for a table layout while our app uses tables everywhere sigh.
Another typical one is that it tends to prefere frontend aggregation and looping of data instead of letting the database and backend deal with it.
Using mix of claude, cursor composer and codex.
Re: When I reject AI code even if it works
#96Not that I disagree with anything here, but...
I wish it were clearer in these kinds of posts how "I use AI code I don't understand" is so different from "I use libraries written by other people I don't understand", or "I work in a large codebase which was 99% written by other people, and I haven't seen all of it", or even "I use software written by other people I don't understand".
Re: When I reject AI code even if it works
#97Earlier quoted context omitted.
All Claude models are huge suck ups. The "you're absolutely right" meme is real even if that exact phrase doesn't show up as much anymore. I don't want to start a fight or anything but IME Codex has a bit more of a spine. If you point out something weird, it sometimes gives a good reason for it. Whereas Claude will always say "whoopsie you're right as always sir" even when it's me who missed something.
IME it's Claude that pushes back, and Codex that just does the thing. It's happened once or twice where I've told Claude bluntly and directly "do this" and it responded "no, here's why that's a bad idea..." Maybe it's just my CLAUDE.md. Not sure if there are sycophancy benchmarks for coding agents
I find the same. Someone posted this benchmark here: https://petergpt.github.io/bullshit-benchmark/viewer/index.v...
It measures whether models push back on bullshit prompts or just go along with it, and Claude models are all the top performers.
Re: When I reject AI code even if it works
#98Earlier quoted context omitted.
Huh? I design everything with plan mode and review every line. Nothing happens to my codebase that I don’t decide should happen. With my way of working, tech debt doesn’t exist because I never have to create it. You’ve made a bunch of assumptions you’re not conscious of. And now you’re blaming me for that. Open your mind, you never know what you might (un)learn.
So then your response has nothing to do with the post. The thesis of the post is (paraphrasing): "if an AI wrote it, and I don't immediately grok it or if the code quality is low, I throw it away, even if on the surface it seems to work, because simply 'working' isn't enough to say a piece of code is acceptable." I'd add as a corollary "and therefore I would never want to be accountable for that code." If you're revi…
I’m in the loop after the work is done to a minimum standard.
The comment was motivated by the complaint that first-draft code from an agent can be brought up in quality significantly with a little bit of engineering.
Re: When I reject AI code even if it works
#99I unterstand the reasons, but I don't think so. I have experience in software development over 20 years now and still developing software daily. Nowadays it's nearly 100℅ AI written. It looks good and works. Sure, you have to guide the AI. But this can be done with custom skills, angent files, code quality guards test cases and so on. Maybe the code looks at the end not as I would have written it, maybe something is too complex implemented. But that's true for large developer teams also. At the end it's way faster and it works. I think, everyone who does not adapt to this new workflow is left behind in professional development soon.
Re: When I reject AI code even if it works
#100I unterstand the reasons, but I don't think so. I have experience in software development over 20 years now and still developing software daily. Nowadays it's nearly 100℅ AI written. It looks good and works. Sure, you have to guide the AI. But this can be done with custom skills, angent files, code quality guards test cases and so on. Maybe the code looks at the end not as I would have written it, maybe something is…
That's cool. Could you share some concrete examples of your successes?