I’ve seen a few articles saying that instead of hating AI, the real quiet programmers young and old are loving it and have a renewed sense of purpose coding with llm helpers (this article was also hating on ed zitiron, which makes sense why it would).
Is this total bullshit? I have to admit, even though it makes me ill, I’ve used llms a few times to help me learn simple code syntax quickly (im and absolute noob who’s wanted my whole life to learn code but cant grasp it very well). But yes, a lot of time its wrong.
From my experience it’s great at doing things that have been done 1000x before (which makes sense given the training data), but when it comes to building something novel it really struggles, especially if there’s 3rd party libraries involved that aren’t commonly used. So you end up spending a lot of time and money hand holding it through things that likely would have been quicker to do yourself.
the 1000x before bit has quite a few sideffects to it as well.
- lesser used languages suffer because there’s not enough training data. this gets annoying quickly when it overrides your static tools and suggests nonsense.
- larger training sets contain more vulnerabilities as most code is pretty terrible and may just be snippets that someone used once and threw away. owasp has a top 10 for a reason. take input validation for example, if I’m working on parsing a string there’s usually context such as is this trusted data or untrusted? if i don’t have that mental model where I’m thinking about the data i might see generated code and think it looks correct but in reality its extremely nefarious.
Its also trained on old stuff.
And because its old, you get some very strange side effects and less maintainability.
It’s decent at reviewing its own code, especially if you give it different lenses to look though.
“Analyze this code and look for security vulnerabilities.” “Analyze this code and look for ways to reduce complexity.”
And then… think about the response like it’s a random dude online reviewing your code. Lots of times it raises good issues but sometimes it tries too hard to find little shit that is at best a sidegrade.
this
The pycharm AI integration completes each line. That’s very useful when you are repeating a well known algorithm and not distracting when you are doing something unusual. So overall, for small things AI is a speed up. I haven’t tried asking chatgpt for bigger coffe chunks, I haven’t had the greatest experience with it up to now and ii don’t want to spend more time debugging than I am already.
Oh man, the Codeium auto complete in PyCharm has been just awful for me. Slow enough that it doesnt come up fast enough that I ever expect it (and rarely comes up when I pause to wait for it) then goes away instantly when I invariably continue typing when it comes up. Then won’t come back if I backspace, erase the word and start retyping it, etc. And competes with the old school pycharm auto complete sometimes which adds another layer of fun.
I’m pretty sure every time you use AI for programming your brain atrophies a little, even if you’re just looking something up. There’s value in the struggle.
So they can definitely speed you up, but be careful how you use it. There’s no value in a programmer who can only blindly recite LLM output.
There’s a balance to be struck in there somewhere, and I’m still figuring it out.
I’m pretty sure every time you use AI for programming your brain atrophies a little, even if you’re just looking something up. There’s value in the struggle.
I assume you were joking but some studies have come out recently that found this is exactly what happens and for more than just programming. (sorry it was a while ago so I dont have links)
Doesn’t sound like they’re joking to me.
There are similar studies on the effects of watching a Youtube video instead of reading a manual.
This is literally the exact same argument made against using books and developing writing.
You can either spend your time generating prompts, tweaking them until you get what you want and then using more prompts to refining the code until you end up with something that does what you want…
or you can just fucking write it yourself. And there’s the bonus of understanding how it works.
AI is probably fine for generating boiler plate code or repetitive simple stuff, but personally I wouldn’t trust it any further than that.
There is a middle ground. I have one prompt I use. I might tweak it a little for different technologies, languages, etc. only so I can fit more standards, documentation and example code in the upload limit.
And I ask it questions rather than asking it to write code. I have it review my code, suggest other ways of doing something, have it explain best practices, ask it to evaluate the maintainability, conformance to corporate standards, etc.
Sometimes it takes me down a rabbit hole when I’m outside my experience (so does Google and stack overflow for what it’s worth), but if you’re executing a task you understand well on your own, it can help you do it faster and/or better.
In the grand scheme of things, I think AI code generators make people less efficient. Some studies have come out that indicate this. I’ve tried to use various AI tools, as I do like fields of AI/ML in general, but they would end up hampering my work in various ways.
I’m not against AI use in software development… But you need to understand what the tools you use actually do.
An LLM is not a dev. It doesn’t have the capability to think on a problem and come up with a solution. If you use an LLM as a dev, you are an idiot pressing buttons on a black box you understand nothing about.
An LLM is a predictive tool. So use it as a predictive tool.
- Boilerplate code? It can do that, yeah. I don’t like to use it that way, but it can do that.
- Implementing a new feature? Maybe, if you’re lucky, it has been trained on enough data that it can put something together. But you need to consider its output completely untrustworthy, and therefore it will require so much reviewing that it’s just better to write it yourself in the first place.
- Implementing something that solves a problem not solved before? Just don’t. Use your own brain, for fuck’s sake. That’s what you have been trained on.
The one use of AI, at the moment, that I actually like and actually improves my workflow is JetBrains’ full line completion AI. It very often accurately predicts what I want to write when it’s boilerplate-ish, and shuts up when I write something original.
Yes they do have the abikity to think and reason just like you (generally mush faster and slightly better)
https://medium.com/@leucopsis/how-gpt-5-compares-to-claude-opus-4-1-fd10af78ef90
96% on the AIME with zero tools. Only reading the question and reasoning through the answer
This is not true. They do not think or reason. They have code that appears to reason, but it definitely is not.
Once it gets off track it doesn’t consider that it is obviously wrong.
A simple math problem can fail and it is really obvious to a human for example.
Absolutely not. This comment shows you have absolutely zero idea how an LLM works.
No, they can’t think and reason. However, they can replicate and integrate the thinking and reasoning of many people who have written about similar problems. And yes, they can do it must faster than we could read a hundred search result pages. And yes, their output looks slightly better than many of us in many cases, because they are often dispensing best practices by duplicating the writings of experts. (In the best cases, that is.)
I’m enjoying it, mostly. It’s definitely great at some tasks and terrible at orhers. You get a feel for what those are after a while:
-
Throwaway projects - proof of concepts, one-off static websites, that kind of thing: absolutely ideal. Weeks of dev becomes hours, and you barely need to bother reviewing it if it works.
-
Research (find a tool for doing XYZ) where you barely know the right search terms: ideal. The research mode on claude.ai is especially amazing at this.
-
Anything where the language is unfamiliar. AI bootstraps past most of the learning curve. Doesn’t help you learn much, but sometimes you don’t care about learning the codebase layout and you just need to fix something.
-
Any medium sized project with a detailed up front description.
What it’s not good for:
- Debugging in a complex system
- Tiny projects (one line change), faster to do it yourself
- Large projects (500+ line change) - the diff becomes unreviewable fairly quickly and can’t be trusted (much worse than the same problem with a human where you can at least trust the intent)
-
The hate is ridiculous as is the hype.
It’s a new tool that is often useful when used correctly. Don’t use it to write entire applications - that’s a recipe for disaster.
But if you’re learning a new language it’s amazing. You have an infinitely patient and immediately available tutor that can teach you a language’s syntax, best practices, etc. I don’t know why that would make you “ill” besides all the shame “real developers” seem to want to lump on anybody who uses AI. If you’re not concerned about passing some “I don’t use an IDE” nerd’s purity test you’ll be fine.
Its an absolute gamechanger, IMO - the research phase of any task is reduced to effectively nothing, and I get massive amounts of work done when I walk away from my desk, because I plan for and keep lists of longer tasks to accomplish during those times.
You need to review every line of code it writes, but that’s no different than it ever was when working with junior devs 🤷♂️ but now I get the code in minutes instead of weeks and the agents actually react to my comments.
We’re using this with a massive monorepo containing hundreds of thousands of lines of code, and in tiny tool repos that serve exactly one purpose. If our code quality checks and standards werent as strict as they have been for the past decade, I think it wouldn’t work well with the monorepo.
The important part is that my company is paying for it - I have no clue what these tools cost. I am definitely more productive, there is absolutely no debate there IMO. Is the extra productivity worth the extra cost? I have literally no idea.
From my experience it’s really great at bootstrapping new projects for you. It’s good at getting you sample files and if you’re using cursor just building out a sample project.
It’s decent at being an alternative to google/SO for syntax or previously encountered errors. There’s a few things it hallucinates but generally it can save time as long as you don’t trust it blindly.
It struggles when you give it complex tasks or not-straightforward items. Or things that require a lot of domain knowledge. I once wanted to see what css classes were still in use across a handful of react components and it just shat the bed.
The people who champion AI as a human replacement will build a quick proof of concept with it and proclaim “oh shit this is awesome!” And not realize that that’s the easy part of software engineering.
I use it mainly to tweak things I can’t be bothered to dig into, like Jekyll or Wordpress templates. A few times I let it run and do a major refactor of some async back-end code. It botched the whole thing. Fortunately, easy to rewind everything from remote git repo.
Last week I started a brand new project, thought I’d have it write the boilerplate starter code. Described in detail what I was looking for. It sat there for ten minutes saying ‘Thinking’ and nothing happened. Killed it and created it myself. This was with Cursor using Claude. I’ve noticed it’s gotten worse lately, maybe because of the increased costs.
Yes. But I’m not paying for premium like some of my cowokres. I use it to avoid the grunt work, and to avoid things I know I’d have to google.
I used some coworkers account for a while and auto complete is amazing. I it guesses wrong you just keep tipping as usual. If its right, hit tab and saves you like 20 seconds.
On the other hand I have cokowkers that do not check the chatgpt output and the PRs make no sense. Example: instead of making a variable type any (which is forbidden in our codebase) they did
Let a : date|number|string|object|(…) = fetchData()
Not total bullshit, but it’s not great for all use cases:
For coding tasks the output looks good on the surface but often I end up changing stuff, meaning it would have been faster up do myself.
For coding I know little about (currently writing some GitHub actions), it’s great at explaining alternatives, pros and cons, to give me a rudimentary understanding of stuff
I’ve also used it to transcribe tutorial screencasts, and then afterwards having a secondary LLM use the transcription to generate documentation (include in prompt: "when relevant, generate examples, use markdown tables, generate plantuml etc)
My favorite use is actually just to help me name stuff. Give it a short description of what the thing does and get a list of decent names. Refine if they’re all missing something.
Also useful for finding things quickly in generated documentation, by attaching the documentation as context. And I use it when trying to remember some of the more obscure syntax stuff.
As for coding assistants, they can help quickly fill in boilerplate or maybe autocomplete a line or two. I don’t use it for generating whole functions or anything larger.
So I get some nice marginal benefits out of it. I definitely like it. It’s got a ways to go before it replaces the programming part of my job, though.
My favorite use is actually just to help me name stuff.
Reverse dictionary lookup, more or less.
Now, that is something LLMs should be actually good at, unlike practically any other thing they’re being sold as being good at.
Definitely depends on the sub-sector of the industry you’re in. There’s no shortage of stories of people who swear by it, or who are having it forced on them by management.
Me personally’ I’ve never wanted or been pressured to use it, and I work for a company with “AI” in the damn name. To be fair, though, this company was around doing general machine-learning stuff before the current LLM craze exploded. Also, I work with a small team that was only bought by this company a few years ago, and thus far has been allowed to remain practically independent. Also also, the business domain my team works in is finance and accounting, where there’s bot much practical application for ML, and where you REALLY can’t afford to fuck around and find out, with business data.
I’m somewhat new to the field ~1.5 years, so my opinion doesn’t hold too much weight.
But in the embedded field I’ve found AI to not be as helpful as it seems to be for many others. The one BIG thing is has helped me with is I can give it a data sheet and it’ll spit out all the register fields that I need, or help me quickly find information that I’m too lazy to Ctrl-f, which saves a couple minutes.
It has not proven it’s worth when it comes to the firmware itself. I’ve tried to get it to instantiate some peripheral instances and they never ended up working, no matter how I phrased the prompt or what context i’ve given it.
