This isn’t so much about coding as it is about architecting code. As I wrote this week, it’s all about planning and a critical viewpoint:
After months of coding with LLMs, I'm going back to using my brain
61–70 of 229 posts
Re: After months of coding with LLMs, I'm going back to using my brain
#62This rings true to me. I still use LLMs heavily . However, I now follow two rules: * Do not delegate any deep thought to them. For example, when thinking through a difficult design problem, I do it myself. * Deeply review and modify any code they generate. I go through it line-by-line and edit it thoroughly. I have to do this because I find that much of what they generate is verbose, overly defensive, etc. I don't ca…
> Deeply review and modify any code they generate. I go through it line-by-line and edit it thoroughly This is the issue, right? If you have to do this, are you saving any time?
I believe this depends on the individual. For me, yeah, I am. But I do have colleagues who wouldn’t be.
Re: After months of coding with LLMs, I'm going back to using my brain
#63I don't get the whole "all-in" mentality around LLMs. I'm an iOS dev by trade, I continue to do that as I always have. The difference now is I'll use an LLM to quickly generate a one-off view based on a design. This isn't a core view of an app, the core functionality, or really anything of importance. It's a view that promotes a new feature, or how to install widgets, or random things. This would normally take me 30-…
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 for 15+ years. I’ve lived through JetBrains IDEs, and switching to VS Code took me days. If you’re coming from a heavily customized Vim setup, the adjustment will be harder. I don’t tolerate flaky output, and I work on a mix of greenfield and legacy systems. Yes, greenfield is more LLM-friendly, but I still get plenty of value from LLMs when navigating and extending mature codebases.
What frustrates me is how polarized these conversations are. There are valid insights on both sides, but too many posts frame their take as gospel. The reality is more nuanced: LLMs are a tool, not a revolution, and their value depends on how you integrate them into your workflow, regardless of experience level.
Re: After months of coding with LLMs, I'm going back to using my brain
#64I don't get the whole "all-in" mentality around LLMs. I'm an iOS dev by trade, I continue to do that as I always have. The difference now is I'll use an LLM to quickly generate a one-off view based on a design. This isn't a core view of an app, the core functionality, or really anything of importance. It's a view that promotes a new feature, or how to install widgets, or random things. This would normally take me 30-…
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…
I've got over 30 years of professional development experience, and I've found LLMs most useful for
* Figuring out how to write small functions (10 lines) in canonical form in a language that I don't have much experience with. This is so I don't end up writing Rust code as if it were Java.
* Writing small shell pipelines that rely on obscure command line arguments, regexes, etc.
Re: After months of coding with LLMs, I'm going back to using my brain
#65The 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, refactoring etc.)
Re: After months of coding with LLMs, I'm going back to using my brain
#66Earlier 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…
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.
I basically learned programming by ExpertSexchange, Google (and Altavista...), SourceForge and eventually StackOverflow + GitHub. Many people with more experience than me at the time always told me I was making a deal with the devil since I searched so much, didn't read manuals and asked so many questions instead of thinking for myself.
~15 years later, I don't think I'm worse off than my peers who stayed away from all those websites. Doing the right searches is probably as important as being able to read manuals properly today.
Re: After months of coding with LLMs, I'm going back to using my brain
#67I have been trying LLMs in a couple of new small projects recently.
I got more success that I hoped for, but I had to adjust my usage to be effective.
First of all, treat the LLM as a less experienced programmer. Don't trust it blindly but always make code review of its changes. This gives several benefits.
1) It keeps you in touch with the code base, so when need arise you can delve into it without too much trouble
2) You catch errors (sometimes huge ones) right away, and you can have them fixed easily
3) You can catch errors on your specification right away. Sometimes I forget some detail and I realize it only when reviewing, or maybe the LLMs did actually handle it, and I can just tell it to update the documentation
4) You can adjust little by little the guidelines for the LLM, so that it won't repeat the same "mistakes" (wrong technical decisions) again.
In time you get a feeling of what it can and cannot do, where you need to be specific and where you know it will get it right, or where you don't need to go into detail. The time required will be higher than vibe coding, but decreases over time and still better than doing by myself.
There is another important benefit for me in using an LLM. I don't only write code, I do in fact many other things. Calls, writing documentation, discussing requirements etc. Going back to writing code requires a change of mental state and to recall into memory all the required knowledge (like how is the project structured, how to use some apis etc.). If I can do two hours of coding it is ok, but if the change is small, it becomes the part where I spend the majority of time and mental energy.
Or I can ask the LLM to make the changes and review them. Seeing the code already done requires less energy and will help me reminding stuff.
Re: After months of coding with LLMs, I'm going back to using my brain
#68I don't get the whole "all-in" mentality around LLMs. I'm an iOS dev by trade, I continue to do that as I always have. The difference now is I'll use an LLM to quickly generate a one-off view based on a design. This isn't a core view of an app, the core functionality, or really anything of importance. It's a view that promotes a new feature, or how to install widgets, or random things. This would normally take me 30-…
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…
> until you've learned to use it
You have the copilot mode which takes no learning at all which might give you some speedup, especially if you are doing repetitive stuff, it might even 10x+ you.
You have cmdk mode which you need to prompt and seems to he a lobotomized version of chat. I find putting comments and waiting for the copilot mode to kick in better as then the way we got there is saved.
Then there is agentic editing chat: that is the timewaster you speak off I believe, but what is there to learn? Sometimes it generates a metric ton of code, including in legacy massive code bases, that help, and often it just cannot do whatever.
I don't think these cases you make, or at least, when the second one goes beyond the basics, are different. There is nothing to learn except that you need read all the code, decide what you want in tech detail and ask that of the agentic chat. Anything else fails beyond the basics and 'learning to use it' will be that but if you didn't know that after 5 minutes you definitely didn't do any 'fine tuned pycharm ide', ever.
It is a tool that customizes code it ingested for your case specifically, if it can. That is it. If it never saw a case, it won't solve it, no matter what you 'learn to use'. And I am fine doing that in public: we use LLMs a lot and I can give you very simple cases that, besides (and often even that doesn't work) typing up the exact code, it will never fix with the current models. It just gets stuck doing meaningless changes with confidence.
Re: After months of coding with LLMs, I'm going back to using my brain
#69Earlier 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.
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.
Re: After months of coding with LLMs, I'm going back to using my brain
#70We ahve numerous, well-doocumented cases of LLMs being just plain wrong and/or hallucinating. There is an epidemic of LLM usage in college (and even high school) to the point where lack of critical thinking is becoming a massive problem and will only get worse.
This represents a huge security threat too if code is uncritically applied to code bases. We've seen many examples where people try and influence LLM output (eg [1][2]). These attempts have generally varied from crude to laughably bad but they'll get better.
Is it so hard to imagine prompt injection being a serious security threat to a code base?
That aside, I just don't understand being "all in" on LLMs for coding. Is this really productive? How much boilerplate do you actually write? With good knowledge of a language or framework, that tends to be stuff you can spit out really quickly anyway.
[1]: https://www.theguardian.com/technology/2025/may/16/elon-musk...
[2]: https://www.theguardian.com/technology/2025/jan/28/we-tried-...