I think LLMs are for manufacturing the bricks, not the house.
After months of coding with LLMs, I'm going back to using my brain
211–220 of 229 posts
Re: After months of coding with LLMs, I'm going back to using my brain
#212Earlier quoted context omitted.
> 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…
> Yes, but these lax expectation s are what I don't understand. It's pretty a really, really simple concept. If I have a crazy Typescript error, for instance, I can throw it in and get a much better idea of what's happening. Just because that's not perfect, doesn't mean it isn't helpful. Even if it works 90% of the time, it's still better than 0% of the time (Which is where I was at before). It's like google search w…
Google search without ads... uBlock Origin
Re: After months of coding with LLMs, I'm going back to using my brain
#213Earlier quoted context omitted.
> Yes, but these lax expectation s are what I don't understand. It's pretty a really, really simple concept. If I have a crazy Typescript error, for instance, I can throw it in and get a much better idea of what's happening. Just because that's not perfect, doesn't mean it isn't helpful. Even if it works 90% of the time, it's still better than 0% of the time (Which is where I was at before). It's like google search w…
Google search without ads... uBlock Origin
how does that help compose the results?
Re: After months of coding with LLMs, I'm going back to using my brain
#214Earlier quoted context omitted.
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…
> ExpertSexchange maybe should have added a space somewhere in there?
I thought explicitly using wrong caps would be enough for most people to get it regardless :)
Re: After months of coding with LLMs, I'm going back to using my brain
#215Earlier quoted context omitted.
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 every…
> no they didn't, no one said that
You're right, probably hallucinated memory of much more senior people telling me exactly that.
> i know that because i was around then and everyone was doing the same thing
Damn, we worked together in the same company at that time? Nice to meet you again after all these years. Still thinking of picking up farming once you get out of prison?
Re: After months of coding with LLMs, I'm going back to using my brain
#216Earlier quoted context omitted.
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…
> Would you ever be able to... later have Claude actually use that framework?
Yes, subject to LLM token limitation. I've run into the second half of the problem, where the LLM doesn't know about the latest version of a library, or the new/modified API that version implements. So then the LLM isn't able to write working code for that API. However, if you add the latest docs into the context window, and ask it to generate code, the LLM is now able to generate working code that uses the new semantics.
The preceding steps to complete the example would then be for CoPilot (which is a frontend to various LLMs, including Claude) to generate the new framework, and then generate docs for this new framework.
Re: After months of coding with LLMs, I'm going back to using my brain
#217Earlier quoted context omitted.
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.
Maybe better formatting would show it better to you.
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 5214Re: After months of coding with LLMs, I'm going back to using my brain
#218Earlier quoted context omitted.
> They usually do not care about the implementation. [citation needed] > Code generated by LLM is not that different than pulling in a random npm package or rust crate It's not random, there's an algorithm for picking "good" packages and it's much simpler than reviewing every single line of LLM code.
>> They usually do not care about the implementation. > [citation needed] Everybody agrees that e.g. `make` and autotools is a pile of garbage. It doesn't matter, it works and people use it. > It's not random, there's an algorithm for picking "good" packages and it's much simpler than reviewing every single line of LLM code. But you don't need to review every single line of LLM code just as you don't need to review e…
If a human wrote it, I can be fairly sure that the human meant it to do what it is advertised as doing. If I run it through its paces and it seems to work, that gives me some confidence that the person who wrote it understood the problem and solved it competently, which allows me to guess that all the parts of it I haven't tested are also likely to work.
If an LLM wrote it, I know that it is a stream of plausible bullshit generated by a statistical model in response to my prompt, whose function may or may not have anything to do with my intent, because the machine which emitted it lacks any capacity to have intentions or to reason through the consequences of its choices. If I run the code through its paces and the basics seem to work, that tells me absolutely nothing about the rest of it. All I can count on is that the code will appear to be plausible, and I have no way of knowing without careful review whether the assumptions baked into it are sane and fit for purpose.
Re: After months of coding with LLMs, I'm going back to using my brain
#219Earlier quoted context omitted.
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 i…
> In an era where an LLM can hallucinate (present you a defect) with 100% conviction, (...) I think you're trying very hard to find anything at all to criticize LLMs and those who use them, but all you manage to come up with is outlandish, "grasping at straws" arguments. Yes, it's conceivable that LLMs can hallucinate. How often do they do, though? In my experience, not that much. In the rare cases they do, it's easy…
Your made up stories are not convincing. You are coming off as one of the block-chain bros desperately trying to claim “you just don’t get it because I’m smarter than you”
Re: After months of coding with LLMs, I'm going back to using my brain
#220Earlier quoted context omitted.
> LLMs are great for junior, fast-shipping devs; less so for experienced, meticulous engineers Is that not true? That feels sufficiently nuanced and gives a spectrum of utility, not binary one and zero but "10x" on one side and perhaps 1.1x at the other extrema. The reality is slightly different - "10x" is SLoC, not necessarily good code - but the direction and scale are about right.
That feels like the opposite of being true. Juniors have, by definition, little experience - the LLM is effectively smarter than them and much better at programming, so they're going to be learning programming skills from LLMs, all while futzing about not sure what they're trying to express. People with many years or even decades of hands-on programming experience, have the deep understanding and tacit knowledge that…
I don't think junior vs senior is actually that well defined. There are met "senior" 30 year old programmers and "junior" 30 year olds (who have also been programming for ~2 decades).