Live data from Hacker News

After months of coding with LLMs, I'm going back to using my brain

albertofortin.com

181–190 of 229 posts

Re: After months of coding with LLMs, I'm going back to using my brain

#181
post #39

Off-topic: may I ask, why PHP + MySQL is no longer considered suitable to you? It's hard to say without specifics, but simply upgrading from MySQL to PostgreSQL without rewriting the PHP codebase in Go might resolve most of the potential issues.

It's two separate issues: 1) I do a lot of scraping, and Go concurrency + Colly has better performance 2) My DB size is exploding and I have limited budget, and it looks like CH is so much better at compressing data. I recently did a test and for the same table with same exact data, MySQL was using 11GB, ClickHouse 500MB

> MySQL was using 11GB, ClickHouse 500MB

That's pretty typical best case size for weblogs and other time ordered data where column data correlate with time values. You do have to tweak the schema a bit to get there. (Specifically a "good" sort order, codecs, ZSTD instead of LZ4 compression, etc.)

Re: After months of coding with LLMs, I'm going back to using my brain

#182
post #88

> I’ve never used Go or Clickhouse before > I have no concept of Go or Clickhouse best practices. > One morning, I decide to actually inspect closely what’s all this code that Cursor has been writing. It’s not like I was blindly prompting without looking at the end result, but I was optimizing for speed and I hadn’t actually sat down just to review the code. > I’m defaulting to coding the first draft of that function…

That is what vibe coding is. The tweet says "It's not too bad for throwaway projects" but that does not limit the definition, it only limits the advisable application of it.

Vibe coding is “Forget the code even exists; it mostly works for throwaway stuff”. That is clearly not what this person wants.

You can’t pick up vibe coding and then complain that it’s behaving as described or that it isn’t giving you something that wasn’t promised.

Re: After months of coding with LLMs, I'm going back to using my brain

#183
post #88

Earlier quoted context omitted.

That is what vibe coding is. The tweet says "It's not too bad for throwaway projects" but that does not limit the definition, it only limits the advisable application of it.

Vibe coding is “Forget the code even exists; it mostly works for throwaway stuff”. That is clearly not what this person wants. You can’t pick up vibe coding and then complain that it’s behaving as described or that it isn’t giving you something that wasn’t promised.

Don't disagree at all. It was never promised that LLMs could do what he's trying to do. But just because he's holding it wrong doesn't mean that he's not holding it.

Re: After months of coding with LLMs, I'm going back to using my brain

#184
I have also stepped back from LLM coding a bit. I still utilize LLMs for API discussions, maybe 1-off things I would stackoverflow before but I have stepped back a bit from autocomplete everywhere and even agentic flows.

And I feel more productive. I recommend that everyone gives it a try.

As a tenured SW developer in my company my measurements for success are much more than "how much code can I spit out". There are mentoring, refactoring, code readability/mantainability, and quality that are important to my job. I found that LLM generated code was not hitting the necessary bars for me in these areas (agent or code autocompletion) and so I have stepped back from them. The readability point is extra important to me. Having maintained million lines of code products, I have found that readability is more important than writing a ton of code: and LLMs just don't hit the bar here.

When I am playing with side projects that I don't have the same bar on, sure Ill have bolt or lovable generate me some code in combination with cursor or windsurf, but these are low stakes and in some ways I just want to get something on paper.

Re: After months of coding with LLMs, I'm going back to using my brain

#185

The 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 have often had the same thought in response to the effusive praise some people have for their sophisticated, automated code editors.

Re: After months of coding with LLMs, I'm going back to using my brain

#186

Earlier quoted context omitted.

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...

I'm not thinking algorithms. Let's say someone write a new web framework. If there is no code samples available, I don't think whatever is going to be in the documentation will be enough data, then the LLMs doesn't have the training data and won't be able to utilize it.

Would you ever be able to tell e.g. CoPilot: I need a web framework with these specs, go create that framework for me. The later have Claude actually use that framework?

Re: After months of coding with LLMs, I'm going back to using my brain

#187
post #8

I 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-…

As a previous iOS dev I was able to spin up a moderately complex app in a weekend, something that would have taken me probably at least a couple of weeks in the past. I have no idea what you’re on about. I don’t even use cursor and windsurf etc, I’m having chatGPT and Gemini just dump all their outputs into single files and manually breaking them up.

Re: After months of coding with LLMs, I'm going back to using my brain

#188
post #137

Earlier quoted context omitted.

"Code generated by LLM is not that different than pulling in a random npm package or rust crate" So I really hope you don't pull in packages randomly. That sounds like a security risk. Also, good packages tend have a team of people maintaining it. How is that the same exactly?

> So I really hope you don't pull in packages randomly. That sounds like a security risk. It absolutely is, but that is besides the point > Also, good packages tend have a team of people maintaining it. How is that the same exactly? The famously do not https://xkcd.com/2347/

If you're a developer, you do yourself a disservice by describing it this way.

Re: After months of coding with LLMs, I'm going back to using my brain

#189
post #66

Earlier 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.

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 a…

>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.

no they didn't, no one said that

i know that because i was around then and everyone was doing the same thing

also, maybe there's a difference between searching and collating answers and just copy and pasting a solution _without thinking_ at all

Re: After months of coding with LLMs, I'm going back to using my brain

#190

The 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,…

Totally agree! Reading code is harder than writing it, and I think I spend more time reading and trying to understand than I do writing. But this CEO I just met on LinkedIn? "we already have the possibility to both improve our productivity and increase our joy. To do that we have to look at what software engineering is. That might be harder than it looks because the opportunity was hidden in plain sight for decades.…

Ah I got more info. Interesting concept: https://moldabledevelopment.com/
Post reply on HN