Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Generative AI coding tools and agents do not work for me

blog.miguelgrinberg.com

Post reply on HN
Print view View original

131–140 of 464 posts

Re: Generative AI coding tools and agents do not work for me

#131

Post by wiseowise »

nerevarthelame wrote: post #108
lexandstuff wrote: post #54

Great article. The other thing that you miss out on when you don't write the code yourself is that sense of your subconscious working for you. Writing code has a side benefit of developing a really strong mental model of a problem, that kinda gets embedded in your neurons and pays dividends down the track, when doing stuff like troubleshooting or deciding on how to integrate a new feature. You even find yourself solv…

> I think people are getting addicted to not having to expend brain energy to solve problems, and they're mistaking that for productivity. I think that's a really elegant way to put it. Google Research tried to measure LLM impacts on productivity in 2024 [1]. They gave their subjects an exam and assigned them different resources (a book versus an LLM). They found that the LLM users actually took more time to finish t…

You’re twisting results. Just because they took more time doesn’t mean their productivity went down. On the contrary, if you can perform expert task with much less mental resources (which 99% of orgs should prioritize for) then it is an absolute win. Work is extremely mentally draining and soul crushing experience for majority of people, if AI can lower that while maintaining roughly same result with subjects allocating only, say, 25% of their mental energy – that’s an amazing win.

Re: Generative AI coding tools and agents do not work for me

#132

Post by didibus »

You could argue that AI-generated code is a black box, but let's adjust our perspective here. When was the last time you thoroughly reviewed the source code of a library you imported? We already work with black boxes daily as we evaluate libraries by their interfaces and behaviors, not by reading every line.

The distinction isn't whether code comes from AI or humans, but how we integrate and take responsibility for it. If you're encapsulating AI-generated code behind a well-defined interface and treating it like any third party dependency, then testing that interface for correctness is a reasonable approach.

The real complexity arises when you have AI help write code you'll commit under your name. In this scenario, code review absolutely matters because you're assuming direct responsibility.

I'm also questioning whether AI truly increases productivity or just reduces cognitive load. Sometimes "easier" feels faster but doesn't translate to actual time savings. And when we do move quicker with AI, we should ask if it's because we've unconsciously lowered our quality bar. Are we accepting verbose, oddly structured code from AI that we'd reject from colleagues? Are we giving AI-generated code a pass on the same rigorous review process we expect for human written code? If so, would we see the same velocity increases from relaxing our code review process amongst ourselves (between human reviewers)?

Re: Generative AI coding tools and agents do not work for me

#133

Post by tptacek »

smaudet wrote: post #123
tptacek wrote: post #106

I'm fine with anybody saying AI agents don't work for their work-style and am not looking to rebut this piece, but I'm going to take this opportunity to call something out. The author writes "reviewing code is actually harder than most people think. It takes me at least the same amount of time to review code not written by me than it would take me to write the code myself". That sounds within an SD of true for me, to…

I guess my challenge is that "if it was a rote recitation of an idiomatic go function", was it worth writing? There is a certain, style, lets say, of programming, that encourages highly non re-usable code that is both at once boring and tedious, and impossible to maintain and thus not especially worthwhile. The "rote code" could probably have been expressed, succinctly, in terms that border on "plain text", but with…

Yes. More things should be rote recitations. Rote code is easy to follow and maintain. We get in trouble trying to be clever (or DRY) --- especially when we do it too early.

Important tangential note: the eBPF verifier doesn't "cut out the chaff". It rejects good, valid programs. It does not care that the programs are valid or good; it cares that it is not smart enough to understand them; that's all that matters. That's the point I'm making about reviewing LLM code: you are not on the hook for making it work. If it looks even faintly off, you can't hurt the LLM's feelings by killing it.

Re: Generative AI coding tools and agents do not work for me

#134

Post by wiseowise »

susshshshah wrote: post #100
sagarpatil wrote: post #87

Earlier quoted context omitted.

I always use Claude Code to debug issues, there’s no point in trying to do this yourself when AI can fix it in minutes (easy to verify if you write tests first) o3 with new search can do things in 5 mins that will take me at least 30 mins if I’m very efficient. Say what you want but the time savings is real.

How do you know what tests to write if you don’t understand the code?

How do you do TDD without having code in the first place? How do QA verifies without reading the source?

Re: Generative AI coding tools and agents do not work for me

#135

Post by root_axis »

sagarpatil wrote: post #68

What really baffles me is the claims from: Anthropic: 80% of the code is generated by AI OpenAI: 70-80% Google/Microsoft: 30%

The use of various AI coding tools is so diffuse that there isn't even a practical way to measure this. You can be assured those numbers are more or less napkin math based on some arbitrary AI performance factor applied to the total code writing population of the company.

Re: Generative AI coding tools and agents do not work for me

#136

Post by didibus »

wiseowise wrote: post #131
nerevarthelame wrote: post #108

Earlier quoted context omitted.

> I think people are getting addicted to not having to expend brain energy to solve problems, and they're mistaking that for productivity. I think that's a really elegant way to put it. Google Research tried to measure LLM impacts on productivity in 2024 [1]. They gave their subjects an exam and assigned them different resources (a book versus an LLM). They found that the LLM users actually took more time to finish t…

You’re twisting results. Just because they took more time doesn’t mean their productivity went down. On the contrary, if you can perform expert task with much less mental resources (which 99% of orgs should prioritize for) then it is an absolute win. Work is extremely mentally draining and soul crushing experience for majority of people, if AI can lower that while maintaining roughly same result with subjects allocat…

If I follow what you are saying, employers won't see any benefits, but employees, while they will take the same time and create the same output in the same amount of time, will be able to do so at a reduced mental strain?

Personally, I don't know if this is always a win, mostly because I enjoy the creative and problem solving aspect of coding, and reducing that to something that is more about prompting, correcting, and mentoring an AI agent doesn't bring me the same satisfaction and joy.

Re: Generative AI coding tools and agents do not work for me

#137

Post by JimDabell »

skydhash wrote: post #35
waprin wrote: post #19

To some degree, traditional coding and AI coding are not the same thing, so it's not surprising that some people are better at one than the other. The author is basically saying that he's much better at coding than AI coding. But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher ski…

> But it's important to realize that AI coding is itself a skill that you can develop. It's not just , pick the best tool and let it go. Managing prompts and managing context has a much higher skill ceiling than many people realize No, it's not. It's something you can pick in a few minutes (or an hour if you're using more advanced tooling, mostly spending it setting things up). But it's not like GDB or using UNIX as…

> It's something you can pick in a few minutes (or an hour if you're using more advanced tooling, mostly spending it setting things up).

This doesn’t give you any time to experiment with alternative approaches. It’s equivalent to saying that the first approach you try as a beginner will be as good as it possibly gets, that there’s nothing at all to learn.

Re: Generative AI coding tools and agents do not work for me

#138

Post by root_axis »

euleriancon wrote: post #96
abenga wrote: post #90

Earlier quoted context omitted.

You do not need to review every line of every package you use, just the subset of the interface you import/link and use. You have to review every line of code you commit into your project. I think attempting to equate the two is dishonest dissembling.

To me, the point the friend is making is, just like you said, that you don't need to review every line of code in a package, just the interface. The author misses the point that there truly is code that you trust without seeing it. At the moment AI code isn't as trustworthy as a well tested package but that isn't intrinsic to the technology, just a byproduct of the current state. As AI code becomes more reliable, it…

> At the moment AI code isn't as trustworthy as a well tested package but that isn't intrinsic to the technology, just a byproduct of the current state

This remains to be seen. It's still early days, but self-attention scales quadratically. This is a major red flag for the future potential of these systems.

Re: Generative AI coding tools and agents do not work for me

#139

Post by bluefirebrand »

112233 wrote: post #128
tptacek wrote: post #106

I'm fine with anybody saying AI agents don't work for their work-style and am not looking to rebut this piece, but I'm going to take this opportunity to call something out. The author writes "reviewing code is actually harder than most people think. It takes me at least the same amount of time to review code not written by me than it would take me to write the code myself". That sounds within an SD of true for me, to…

This is radical and healthy way to do it. Obviously wrong — reject. Obviously right — accept. In any other case — also reject, as non-obvious. I guess it is far removed from the advertized use case. Also, I feel one would be better off having auto-complete powered by LLM in this case.

> Obviously right — accept.

I don't think code is ever "obviously right" unless it is trivially simple

Re: Generative AI coding tools and agents do not work for me

#140

Post by smaudet »

tptacek wrote: post #133
smaudet wrote: post #123

Earlier quoted context omitted.

I guess my challenge is that "if it was a rote recitation of an idiomatic go function", was it worth writing? There is a certain, style, lets say, of programming, that encourages highly non re-usable code that is both at once boring and tedious, and impossible to maintain and thus not especially worthwhile. The "rote code" could probably have been expressed, succinctly, in terms that border on "plain text", but with…

Yes. More things should be rote recitations . Rote code is easy to follow and maintain. We get in trouble trying to be clever (or DRY) --- especially when we do it too early. Important tangential note: the eBPF verifier doesn't "cut out the chaff". It rejects good, valid programs . It does not care that the programs are valid or good; it cares that it is not smart enough to understand them; that's all that matters. T…

> We get in trouble trying to be clever (or DRY)

Certainly, however:

> That's the point I'm making about reviewing LLM code: you are not on the hook for making it work

The second portion of your statement is either confusing (something unsaid) or untrue (you are still ultimately on the hook).

Agentic AI is just yet another, as you put it way to "get in trouble trying to be clever".

My previous point stands - if it was that cut and dry, then a (free) script/library could generate the same code. If your only real use of AI is to replace template systems, congratulations on perpetuating the most over-engineered template system ever. I'll stick with a provable, free template system, or just not write the code at all.

Post reply on HN