After spending 1000s of dollars on 3 projects that I thought I could finish in a weeks :) with agents with cline, I reached similar conclusion. Best use cases I have seen it work is for good commit messages, templated documentation and cursory understanding existing code base. Shine wore off on me too.
After months of coding with LLMs, I'm going back to using my brain
151–160 of 229 posts
Re: After months of coding with LLMs, I'm going back to using my brain
#152Earlier quoted context omitted.
Agreed but the 1 year JS dev should know they're making a deal with the devil in terms of building their skillset long term.
Maybe. But I also think that ignoring AI tools will hamper your long-term skillsets, as our profession adapts to these new tools.
Why would that be the case? If anything, each successive generation of AI tools gets easier to use and requires less prompt fiddling. I picked up Cursor and was comfortable with it in 20 minutes.
I'm not sure there's much of a skillset to speak of for these tools, beyond model-specific tricks that evaporate after a few updates.
Re: After months of coding with LLMs, I'm going back to using my brain
#153Earlier quoted context omitted.
Fair enough but if you have to show up in the comments clarifying that your clearly delineated “IF this THEN that” post wasn’t meant to be read as a hard divide, maybe the examples weren’t doing the work you thought they were. You can’t sketch a two-point graph and then be surprised people assume it’s linear. Again I think the high level premise is correct as I already said, the delivery falls flat though. Your more…
I and others understood it perfectly well. Maybe the problem wasn’t with the post.
And I along with others who upvoted me did not. What’s your point? Seems like you have none and instead just want to point fingers.
Re: After months of coding with LLMs, I'm going back to using my brain
#154Earlier quoted context omitted.
16 year python dev who's done all that, lead multiple projects from inception to success, and I rarely manually code anymore. I can specify precisely what I want, and how I want it built (this is the key part), stub out a few files and create a few directories, and let an agent run wild but configured for static analysis tools/test suite to run after every iteration with the instructions to fix their mistakes before…
Assuming that your workflow works, and the rest of us just need to learn to use LLMs equally effective, won't that plateau us at the current level of programming? The LLMs learn from examples, but if everyone uses LLMs to generate code, there's no new code to learn new features, libraries or methods from. The next generation of models are just going to be trained on the code generated by it's predecessors with now ne…
If Google's AlphaEvolve is any indication, they already have LLM's writing faster algorithms than humans have discovered.[1]
[1]https://deepmind.google/discover/blog/alphaevolve-a-gemini-p...
Re: After months of coding with LLMs, I'm going back to using my brain
#155Earlier quoted context omitted.
How useful the various tools will be depends on the person and the problem. Take two hypothetical people working on different problems and consider if, for example, Cursor would be useful. IF you're a: * 10 year python dev * work almost entirely on a very large, complex python code base * have a pycharm IDE fine tuned over many years to work perfectly on that code base * have very low tolerance for bugs (stable produ…
16 year python dev who's done all that, lead multiple projects from inception to success, and I rarely manually code anymore. I can specify precisely what I want, and how I want it built (this is the key part), stub out a few files and create a few directories, and let an agent run wild but configured for static analysis tools/test suite to run after every iteration with the instructions to fix their mistakes before…
Let’s see the GitHub project for an easy 10k line day.
Re: After months of coding with LLMs, I'm going back to using my brain
#156Earlier quoted context omitted.
I do a variety of things, including iOS and web. Like you mentioned, LLM results between the two are very different. I can't trust LLM output to even compile, much less work. Just last night, it told me to use an API called `CMVideoFormatDescriptionGetCameraIntrinsicMatrix`. That API is very interesting because it doesn't exist. It also did a great job of digging some deep holes when dealing with some tricky Swift 6…
Honestly, with a lot of HN debating the merits of LLMs for generating code, I wish it were an unwritten rule that everyone states the stack they're using with it. It seems that the people who rave about it creating a whole product line in a weekend are asking it to write them a web iterface using [popular js framework] that connects to [ubiquitous database], and their app is a step or two away from being CRUD. Meanwh…
> Meanwhile, the people who say it's done nothing for them are writing against [proprietary in-house library from 2005].
there's MCP servers now that should theoretically help with that, but that's its own can of worms.
Re: After months of coding with LLMs, I'm going back to using my brain
#157Hypothesis: the actual long-term impact of LLM's on coding will be that more different languages get used, because it reduces the "ugh I don't want to have to learn all that" psychological obstacle that prevents programmers experienced in one language from learning another. We should be using different languages for different tasks, but the push has always been to try to get One Language To Rule Them All. Ten years a…
counter hypothesis - fewer languages will be used because LLMs will be better at languages with lots of training data I never write python in my day to day but every from-scratch project I've knocked out with Claude code has been in python because that's what it seems to default to if I don't specify anything
Interesting point!
I wonder if this will also mean that new languages (or even algorithms or code patterns) are harder to get adopted, because the mass of existing code (that LLMs learned from) exerts a gravitational force pulling things back down to the status quo.
Re: After months of coding with LLMs, I'm going back to using my brain
#158Earlier quoted context omitted.
How useful the various tools will be depends on the person and the problem. Take two hypothetical people working on different problems and consider if, for example, Cursor would be useful. IF you're a: * 10 year python dev * work almost entirely on a very large, complex python code base * have a pycharm IDE fine tuned over many years to work perfectly on that code base * have very low tolerance for bugs (stable produ…
These all-or-nothing takes on LLMs are getting tiresome. I get the point you’re trying to make, LLMs can be a force multiplier for less experienced devs, but the sweeping generalizations don’t hold up. If you’re okay with a higher tolerance for bugs or loose guardrails, sure, LLMs can feel magical. But that doesn’t mean they’re less valuable to experienced developers. I’ve been writing Python and Java professionally…
This doesn't seem like an "all or nothing" take. This person is trying to be clear about their claims, but they're not trying to state these are the only possible takes. Add the word "probably" after each "then" and I image their intended tone becomes a little clearer.
Re: After months of coding with LLMs, I'm going back to using my brain
#159Earlier quoted context omitted.
16 year python dev who's done all that, lead multiple projects from inception to success, and I rarely manually code anymore. I can specify precisely what I want, and how I want it built (this is the key part), stub out a few files and create a few directories, and let an agent run wild but configured for static analysis tools/test suite to run after every iteration with the instructions to fix their mistakes before…
Let’s see the GitHub project for an easy 10k line day.
Not public on github, but here's the cloc for an easy 5k one day (10k is sweats).
github.com/AlDanial/cloc v 2.04 T=0.05 s (666.3 files/s, 187924.3 lines/s) ------------------------------------------------------------------------------- Language files blank comment code ------------------------------------------------------------------------------- Python 24 1505 1968 5001 Markdown 4 37 0 121 Jinja Template 3 17 2 92 ------------------------------------------------------------------------------- SUM: 31 1559 1970 5214 -------------------------------------------------------------------------------
Note this project also has 199 test cases.
Initial commit for cred:
commit caff2ce26225542cd4ada8e15246c25176a4dc41 Author: redacted Date: Thu May 15 11:32:45 2025 +0800
docs: Add README
Re: After months of coding with LLMs, I'm going back to using my brain
#160Earlier quoted context omitted.
> I get the point you’re trying to make, LLMs can be a force multiplier for less experienced devs, but the sweeping generalizations don’t hold up. If you’re okay with a higher tolerance for bugs or loose guardrails, sure, LLMs can feel magical. But that doesn’t mean they’re less valuable to experienced developers. Amen. Seriously. They're tools. Sometimes they work wonderfully. Sometimes, not so much. But I have DEFI…
> Amen. Seriously. They're tools. Sometimes they work wonderfully. Sometimes, not so much. But I have DEFINITELY found value. And I've been building stuff for over 15 years as well. Yes, but these lax expectation s are what I don't understand. What other tools in software sometimes work and sometimes don't that you find remotely acceptable? Sure all tools have bugs, but if your compiler had the same failure rate and…
People are way too quick to defend LLMs here, because it's exactly on point.
In an era where an LLM can hallucinate (present you a defect) with 100% conviction, and vibe coders can ship code of completely unknown quality with 100% conviction, the bar by definition has to have been set lower.
Someone with experience will still bring something more than just LLM-written code to the table, and that bar will stay where it is. The people who don't have experience won't even feel the shortcomings of AI because they won't know what it's getting wrong.