Generative AI coding tools and agents do not work for me • Hacker News Board

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

#151

Post by bluefirebrand » Tue, Jun 17, 2025, 5:12 AM UTC

andrewstuart wrote: post #127

He’s saying it’s not faster because he needs to impose his human analysis on it which is slow. That’s fine, but it’s an arbitrary constraint he chooses, and it’s wrong to say AI is not faster. It is. He just won’t let it be faster. Some won’t like to hear this, but no-one reviews the machine code that a compiler outputs . That’s the future, like it or not. You can’t say compilers are slow because I add on the time I…

> no-one reviews the machine code that a compiler outputs

That's because compilers are generally pretty trustworthy. They aren't necessarily bug free, and when you do encounter compiler bugs it can be extremely nasty, but mostly they just work

If compilers were wrong as often as LLMs are, we would be reviewing machine code constantly

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

#152

Post by autobodie » Tue, Jun 17, 2025, 5:14 AM UTC

kenjackson wrote: post #114

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 can read code much faster than I can write it. This might be the defining line for Gen AI - people who can read code faster will find it useful and those that write faster then they can read won’t use it.

I think that's wrong. I only have to write code once, maybe twice. But when using AI agents, I have to read many (5? 10? I will always give up before 15) PRs before finding one close enough that I won't have to rewrite all of it. This nonsense has not saved me any time, and the process is miserable.

I also haven't found any benefit in aiming for smaller or larger PRs. The aggregare efficiency seems to even out because smaller PRs are easier to weed through but they are not less likely to be trash.

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

#153

Post by animex » Tue, Jun 17, 2025, 5:15 AM UTC

I write mostly boilerplate and I'd rather have the AI do it. The AI is also slow, which is great, which allows me to run 2 or 3 AI workspaces working on different tickets/problems at the same time.

Where AI especially excels is helping me do maintenance tickets on software I rarely touch (or sometimes never have touched). It can quickly read the codebase, and together we can quickly arrive at the place where the patch/problem lies and quickly correct it.

I haven't written anything "new" in terms of code in years, so I'm not really learning anything from coding manually but I do love solving problems for my customers.

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

#154

Post by materielle » Tue, Jun 17, 2025, 5:15 AM UTC

didibus wrote: post #132

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 i…

I’m not sure that the library comparison really works.

Libraries are maintained by other humans, who stake their reputation on the quality of the library. If a library gets a reputation of having a lax maintainer, the community will react.

Essentially, a chain of responsibility, where each link in the chain has an incentive to behave well else they be replaced.

Who is accountable for the code that AI writes?

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

#155

Post by autobodie » Tue, Jun 17, 2025, 5:22 AM UTC

monero-xmr wrote: post #126

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 mostly just approve PRs because I trust my engineers. I have developed a 6th sense for thousand-line PRs and knowing which 100-300 lines need careful study. Yes I have been burned. But 99% of the time, with proper test coverage it is not an issue, and the time (money) savings have been enormous. "Ship it!" - me

Haha, doing this with AI will bury you in a very deep hole.

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

#156

Post by theK » Tue, Jun 17, 2025, 5:26 AM UTC

monero-xmr wrote: post #126

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 mostly just approve PRs because I trust my engineers. I have developed a 6th sense for thousand-line PRs and knowing which 100-300 lines need careful study. Yes I have been burned. But 99% of the time, with proper test coverage it is not an issue, and the time (money) savings have been enormous. "Ship it!" - me

I think this points out the crux of the difference of collaborating with other devs vs collaborating with am AI. The article correctly States that the AI will never learn your preferences or idiosyncrasies of the specific projects/company etc because it effectively is amnesic. You cannot trust the AI the same you trust other known collaborators because you don't have a real relationship with it.

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

#157

Post by edg5000 » Tue, Jun 17, 2025, 5:27 AM UTC

A huge bottleneck seems the lack of memory between sessions, at least with Claude Code. Sure, I can write things into a text file, but it's not the same as having an AI actually remember the work done earlier.

Is this possible in any way today? Does one need to use Llama or DeepSeek, and do we have to run it on our own hardware to get persistence?

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

#158

Post by adastra22 » Tue, Jun 17, 2025, 5:28 AM UTC

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?

I’m not sure I understand this statement. You give your program parameters X and expect result Y, but instead get Z. There is your test, embedded in the problem statement.

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

#159

Post by autobodie » Tue, Jun 17, 2025, 5:28 AM UTC

serpix wrote: post #130

notnullorvoid wrote: post #120

Earlier quoted context omitted.

Is it a skill worth learning though? How much does the output quality improve? How transferable is it across models and tools of today, and of the future? From what I see of AI programming tools today, I highly doubt the skills developed are going to transfer to tools we'll see even a year from now.

Regarding using AI tools for programming it is not a one-for-all choice. You can pick a grunt work task such as "Tag every such and such terraform resource with a uuid" and let it do just that. Nothing to do with quality but everything to do with a simple task and not having to bother with the tedium.

Why use AI to do something so simple? You're only increasing the possibility that it gets done wrong. Multi-cursor editing wil be faster anyway.

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

#160

Post by adastra22 » Tue, Jun 17, 2025, 5:30 AM UTC

jumploops wrote: post #12

hooverd wrote: post #5

Earlier quoted context omitted.

Is anybody doing cool hybrid interfaces? I don't actually want to do everything in conversational English, believe it or not.

My workflow is to have spec files (markdown) for any changes I’m making, and then use those to keep Claude on track/pull out of the trees. Not super necessary for small changes, but basically a must have for any larger refactors or feature additions. I usually use o3 for generating the specs; also helpful for avoiding context pollution with just Claude Code.

I do similar and find that this is the best compromise that I have tried. But I still find myself nodding along with OP. I am more and more finding that this is not actually faster, even though it certainly seems so.