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

I am uninstalling AI coding assistants from my personal computer

sam.sutch.net

Post reply on HN
Print view View original

31–40 of 44 posts

Re: I am uninstalling AI coding assistants from my personal computer

#31

Post by jaredcwhite »

cheevly wrote: post #7
bluefirebrand wrote: post #4

I haven't had nearly the same experience of success with AI. I'm often accused of letting my skepticism hold me back from really trying it properly, and maybe that's true. I certainly could not imagine going months without writing any code, letting the AI just generate it while I prompt My work is pushing these tools hard and it is taking a huge toll on me. I'm constantly hearing how life changing this is, but I cann…

And the irony is that those of us using AI to amplify our output to produce at exponential speeds feel like your comments are gaslighting us instead! Ive never seen such an outright divide in practitioners of a technology in terms of perception and outcomes. I got into LLMs super early, using them daily since 2022; so that may have bolstered the way I’ve augmented my approaches and tooling. Now almost everything I bu…

> amplify our output to produce at exponential speeds

I think I blacked out when my brain tried to process this phrase.

Nothing personal, but I automatically discount all claims like this (something something require extraordinary evidence and all that…).

Re: I am uninstalling AI coding assistants from my personal computer

#32

Post by geoka9 »

bluefirebrand wrote: post #4

I haven't had nearly the same experience of success with AI. I'm often accused of letting my skepticism hold me back from really trying it properly, and maybe that's true. I certainly could not imagine going months without writing any code, letting the AI just generate it while I prompt My work is pushing these tools hard and it is taking a huge toll on me. I'm constantly hearing how life changing this is, but I cann…

My "agentic" experience is mostly Aider, working across a Golang webapp codebase. I've mostly used Gemini (whatever model Aider chooses to use at the moment).

Most of my experience has been similar to yours. But yesterday, out of the blue, it spit out a commit that I accepted almost verbatim (just added some line breaks and stuff). I was actually really surprised: not only it followed the existing codebase conventions and variable naming style, but also introduced a couple of patterns that I haven't thought of (and I liked).

But it also charged me $2 for the privilege :) (On a related note, Gemini API has become noticeably more expensive compared to, say, a month ago.)

I find that with Aider managing context (what files you add to it) can make all the difference.

Re: I am uninstalling AI coding assistants from my personal computer

#33

Post by NathanKP »

fakedang wrote: post #23
NathanKP wrote: post #20

Earlier quoted context omitted.

I think the author's definition of "creating" is just too narrow. A gardener can get tremendous satisfaction from watching their plants grow from the bed of soil that they prepared, even if there is not as much weeding or watering to do later on in the growth cycle. A parent can get tremendous satisfaction from watching their child continue to grow and develop, even after the child is no longer an infant who requires…

Cue me, cursing the AI with a choice selection of names, when my AI code writer of choice decides to change core files that I had explicitly told it not to touch earlier in the chat. Guess I will not be a good parent lol.

Negative instructions do not work as well as positive ones. If you tell the LLM "don't do this" you only put the idea of doing that into it's context. (Surprisingly the same goes for human toddlers.... the AI is just in it's toddler phase).

Not to mention that context length is limited, so if you told it something "earlier" then your statement has probably already dropped off the end of the context window.

What works better is to prompt with positive instructions of intent like:

"Working exclusively in file(s) ____ and ____ implement ____ in a manner similar to how it is done in example file ______".

I start a fresh chat for each prompt, with fresh context, and try to keep all instructions embedded within a single prompt rather than relying on fragile past state that may or may not have dropped off the end of the context window. If there is something like "don't touch these core files" or "work exclusively in folder X" that I want it to always consider, then I add it as a system prompt or global rule file (ensures that the instruction gets included automatically on every prompt).

And don't get me wrong I get frustrated with AI sometimes too, but the frustration has declined dramatically as I've learned how to prompt it: appropriate task sizes, how to use positive statements rather than negative, how to gather the appropriate context for it to steer behavior and output, etc.

Re: I am uninstalling AI coding assistants from my personal computer

#34

Post by sokoloff »

geoka9 wrote: post #32
bluefirebrand wrote: post #4

I haven't had nearly the same experience of success with AI. I'm often accused of letting my skepticism hold me back from really trying it properly, and maybe that's true. I certainly could not imagine going months without writing any code, letting the AI just generate it while I prompt My work is pushing these tools hard and it is taking a huge toll on me. I'm constantly hearing how life changing this is, but I cann…

My "agentic" experience is mostly Aider, working across a Golang webapp codebase. I've mostly used Gemini (whatever model Aider chooses to use at the moment). Most of my experience has been similar to yours. But yesterday, out of the blue, it spit out a commit that I accepted almost verbatim (just added some line breaks and stuff). I was actually really surprised: not only it followed the existing codebase convention…

That $2 represents how many minutes of your annual labor? 2 minutes? Less than 1 if you account for all the non-coding drag on your tota working time?

Re: I am uninstalling AI coding assistants from my personal computer

#35

Post by GianFabien »

Macha wrote: post #26

> I wonder if some “actual" artists (as in, those people who create the kind of art most people would recognize) have gone through a similar arc of realizing the emptiness of creating with AI tools. My impression is that artists are even more hostile than the most AI-skeptic of software engineers. In large part, this is likely because the economic argument doesn't hold much sway. For the large majority of artists, it…

The way I see it: Painters (as in artists) paint with brushes not spray guns.

The industrial scale painting robots work well for painting cars coming off an assembly line, but not for landscapes nor portraits.

Automation (not just AI, but in general) works well for highly structured, repetitious work but not for creative expression.

Re: I am uninstalling AI coding assistants from my personal computer

#36

Post by glouwbug »

bluefirebrand wrote: post #27
glouwbug wrote: post #25

Earlier quoted context omitted.

My approach has always been to consult 3 different models to get my understanding on the right path and then do the rest myself. Are we really just doing blind copy pastes? As an example, I recently was able to prototype several different one dimensional computational fluid dynamic GLSL shaders. Claude outputted everything with vec3s, and so the flux math matched what you’d see in the theory. It’s rapid iteration and…

> My approach has always been to consult 3 different models to get my understanding on the right path and then do the rest myself. Are we really just doing blind copy pastes For me, if I spent the time testing 3 different models I would definitely be slower than writing the code myself

But I'm not writing code. It's research with iteration. Punching out manual CFD is time consuming

Re: I am uninstalling AI coding assistants from my personal computer

#37

Post by GianFabien »

bluefirebrand wrote: post #4

I haven't had nearly the same experience of success with AI. I'm often accused of letting my skepticism hold me back from really trying it properly, and maybe that's true. I certainly could not imagine going months without writing any code, letting the AI just generate it while I prompt My work is pushing these tools hard and it is taking a huge toll on me. I'm constantly hearing how life changing this is, but I cann…

>letting the AI just generate it while I prompt

But isn't prompting and iterating another way of instructing the computer to do what you want? Perhaps we could view it as a step up in the level of abstraction we work at.

We had similar arguments when high-level languages were introduced. Experienced programmers of that era maintained that they could write better programs in assembly language than in COBOL/FORTRAN/PL-I/Pascal etc. Yet even today we still need core portions of code written in assembler, but not much.

Re: I am uninstalling AI coding assistants from my personal computer

#38

Post by bluefirebrand »

GianFabien wrote: post #37
bluefirebrand wrote: post #4

I haven't had nearly the same experience of success with AI. I'm often accused of letting my skepticism hold me back from really trying it properly, and maybe that's true. I certainly could not imagine going months without writing any code, letting the AI just generate it while I prompt My work is pushing these tools hard and it is taking a huge toll on me. I'm constantly hearing how life changing this is, but I cann…

>letting the AI just generate it while I prompt But isn't prompting and iterating another way of instructing the computer to do what you want? Perhaps we could view it as a step up in the level of abstraction we work at. We had similar arguments when high-level languages were introduced. Experienced programmers of that era maintained that they could write better programs in assembly language than in COBOL/FORTRAN/PL-…

But we aren't moving up a layer of abstraction here

We are operating at the same level of abstraction, just with tools to generate high volumes of inconsistent quality of it for us

Edit: It would have to produce a lot higher quality a lot more consistently for me to seriously consider moving up to the "LLM prompt" abstraction layer permanently. As it is I think I'm just better off writing the code myself

Re: I am uninstalling AI coding assistants from my personal computer

#39

Post by Jotalea »

I agree. Using AI for development is addictive, once you start you cannot stop. It has harmed me, stunting my skills; just like the lack of exercise leads to physical decline, my coding muscles atrophied due to the lack of practice this dependency caused. And since tech is my only real strength, and I'm not what you'd call "successful", feeling stuck at the one thing I'm supposed to be good at makes me feel useless, makes me feel like a burden. And the worst thing? I'm unable to get back on track. I've tried getting back to coding manually, but I simply can't do it anymore. Last time I programmed anything without using AI was in 2023, on a Scratch project, simply because AI could not write Scratch blocks.

But at least I can now ship (shitty) code a lot faster.

Re: I am uninstalling AI coding assistants from my personal computer

#40

Post by fakedang »

NathanKP wrote: post #33
fakedang wrote: post #23

Earlier quoted context omitted.

Cue me, cursing the AI with a choice selection of names, when my AI code writer of choice decides to change core files that I had explicitly told it not to touch earlier in the chat. Guess I will not be a good parent lol.

Negative instructions do not work as well as positive ones. If you tell the LLM "don't do this" you only put the idea of doing that into it's context. (Surprisingly the same goes for human toddlers.... the AI is just in it's toddler phase). Not to mention that context length is limited, so if you told it something "earlier" then your statement has probably already dropped off the end of the context window. What works…

Thank you! I will keep these in mind.

I realized I was doing it wrong when Cloudflare launched their own prompt spec for their workers implementation. Their proposed pattern is slightly different though: "You need to do this, but you did that. Please fix (with this [optional])". I might try a hybrid approach the next time.

Post reply on HN