I've been experimenting with LLMs for coding / "agentic" editing using Zed over the past month or so. It's another tool in the toolbox, good for prototyping, also good for rote tasks (like upgrading a legacy code base, converting one call to another.) So far I've been most impressed by Claude Sonnet. The jury is still out... I haven't used it for any "work" tasks, only hobby projects, because I don't feel comfortable doing that yet.
After months of coding with LLMs, I'm going back to using my brain
161–170 of 229 posts
Re: After months of coding with LLMs, I'm going back to using my brain
#162LLMs are pretty similar in concept to site builders. They can do the basics reasonably well but if you want anything custom they show their weaknesses.
I have been building a gallery for my site with custom zoom/panning UX to be exactly how I want it (which by the way does not already exist as a library). Figuring out the equations for it is simply impossible for an LLM to do.
I wouldn't be surprised if after the LLM hype we go back to site/app builders being the entry level option.
Re: After months of coding with LLMs, I'm going back to using my brain
#163Earlier 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…
> What other tools in software sometimes work and sometimes don't that you find remotely acceptable?
Searching for relevant info on the Internet can take several attempts, and occasionally I end up not finding anything useful.
My ide intellisense tries to guess what identifier I want and put it at the top of the list, sometimes it guesses wrong.
I've heard that the various package repositories will sometimes deliberately refuse to work for a while because of some nonsense called "rate limiting".
Cloud deployments can fail due to resource availability.
Re: After months of coding with LLMs, I'm going back to using my brain
#164When you have a hammer in your hand everything looks like a nail.
Developing without the knowledge what LLM writes is dangerous. For me having LLM as a tool is like having a few Junior Developers around, that I can advise and work with. If I have a complicated logic that I need to write - I write it. After I wrote it, I can ask LLM to review it, it might be good to find some corner cases in some places. When I need to "move things from one bucket to another", like call API and save to DB - that is a perfect task for LLM, that I can easily review after.
At the same time, LLM is able to write pretty good complicated logic as well for my side projects. I might need to give it a few hints, but the results are amazing.
Re: After months of coding with LLMs, I'm going back to using my brain
#165Earlier quoted context omitted.
The jury is still out on that one. Having a tool that’s embedded into your workflow and shows you how things can be done based on tons of example codebases could help a junior dev quite a lot to learn , not just to produce .
Like anything else with learning, that will be heavily dependent on the individual's level of motivation. Based on the classmates I had in college who were paying to get a CS degree, I'd be surprised if many junior devs already working a paid job put much effort into learning rather than producing.
I wouldn't dismiss the implicit/subconscious aspect of learning by example that occurs when you are "just" producing.
Re: After months of coding with LLMs, I'm going back to using my brain
#166Earlier quoted context omitted.
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.
The guy was nice enough to explain his post that you got confused about. Rather than be thankful you used that as evidence that he was not clear and lectured him on it.
I gently suggested that the problem may have not been with his post but with your understanding. Apparently you missed the point again.
Re: After months of coding with LLMs, I'm going back to using my brain
#167> LLMs are okay at coding, but at scale they build jumbled messes.
This reminds me of the day of Dreamweaver and the like. Everybody loved how quickly they could drag and drop UI components on a canvas, and the tool generated HTML code for them. It was great at the beginning, but when something didn't work correctly, you spent hours looking at spaghetti HTML code generated by the tool.
At least, back then, Dreamweaver used deterministic logic to generate the code. Now, you have AI with the capability to hallucinate...
Re: After months of coding with LLMs, I'm going back to using my brain
#168If and when LLMs are able to complete software development projects autonomously, the first sign probably won't be that your own software development job gets easier. Almost certainly, Google AI, DeepSeek, or OpenAI will notice before you do, and that's when their further progress will be limited only by how fast their GPUs can develop AI software instead of how fast their human SWEs can develop AI software.
Eric Schmidt gave a TED interview about the subject this week. He predicts the US and China bombing each other's data centers.
Re: After months of coding with LLMs, I'm going back to using my brain
#169The thing most LLM maximalists don't realize is that the bottleneck for most people is not code generation, it's code understanding. You may have doubled the speed at which you created something, but you need to pay double that time back in code review, testing and building a mental model of the codebase in your head. And you _need_ to do this if you want to have any chance of maintaining the codebase (i.e. bugfixes,…
I've found LLMs are pretty good at explaining my code back to me.
Re: After months of coding with LLMs, I'm going back to using my brain
#170Earlier quoted context omitted.
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…
This shows nothing.