621–630 of 1001 posts
Often while trying to fall asleep, I'll be thinking something like "I need my app to do such and such".
The next day, instead of forcing myself to start coding, I can literally say to Intelij Junie (using Claude), exactly that: "I need my app to do such and such". I'm often pleasantly surprised by the outcome. And if there's anything that needs to be tweaked, I'm now in the mode of critiquing and editing.
Earlier quoted context omitted.
> non-trivial coding tasks I’ve come back to the idea LLMs are super search engines. If you ask it a narrow, specific question, with one answer, you may well get the answer. For the “non-trivial” questions, there always will be multiple answers, and you’ll get from the LLM all of these depending on the precise words you use to prompt it. You won’t get the best answer, and in a complex scenario requiring highly recurs…
>I’ve come back to the idea LLMs are super search engines. Yes! This is exactly what it is. A search engine with a lossy-compressed dataset of most public human knowledge, which can return the results in natural language. This is the realization that will pop the AI bubble if the public could ever bring themselves to ponder it en masse. Is such a thing useful? Hell yes! Is such a thing intellegent? Certainly NO!
I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…
Have another model review the code, and use that review as automatic feedback?
I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…
> Other people are just less picky than I am I think this is part of it. When coding style has been established among a team, or within an app, there are a lot of extra hoops to jump through, just to get it to look The Right Way, with no detectable benefit to the user. If you put those choices aside and simply say: does it accomplish the goal per the spec (and is safe and scalable[0]), then you can get away with a lo…
Morphing an already decent PR into a different coding style is actually something that LLMs should excel at.
Earlier quoted context omitted.
Agreed, but: There's been a notable jump over the course of the last few months, to where I'd say it's inevitable. For a while I was holding out for them to hit a ceiling where we'd look back and laugh at the idea they'd ever replace human coders. Now, it seems much more like a matter of time. Ultimately I think over the next two years or so, Anthropic and OpenAI will evolve their product from "coding assistant" to "…
There's no chance LLMs will be an engineering team replacement. The hallucination problem is unsolvable and catastrophic in some edge cases. Any company using such a team would be uninsurable and sued into oblivion.
If you want to go further, you can even require the LLM to produce a machine checkable proof that the software is correct. That's beyond the state of the art at the moment, but it's far from 'unsolvable'.
If you hallucinate such a proof, it'll just not work. Feed back the error message from the proof checker to your coding assistant, and the hallucination goes away / isn't a problem.
Earlier quoted context omitted.
What does it tell you that programmers with the credibility of antirez - and who do not have an AI product to sell you - are writing things like this even when they know a lot of people aren't going to like reading them?
That is an argument to authority. There is a large enough segment of folks who like to be confirmed in either direction. Doesn't make the argument itself correct or incorrect. Time will tell though.
I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…
> How do I feel, about all the code I wrote that was ingested by LLMs? I feel great to be part of that, because I see this as a continuation of what I tried to do all my life: democratizing code, systems, knowledge. LLMs are going to help us to write better software, faster, and will allow small teams to have a chance to compete with bigger companies. You might feel great, thats fine, but I dont. And software quality…
Is there some metric for this?
I don't understand the stance that AI currently is able to automate away non-trivial coding tasks. I've tried this consistently since GPT 3.5 came out, with every single SOTA model up to GPT 5.1 Codex Max and Opus 4.5. Every single time, I get something that works, yes, but then when I start self-reviewing the code, preparing to submit it to coworkers, I end up rewriting about 70% of the thing. So many important deta…
The biggest frustration with LLMs for me is people telling me I'm not promoting it in a good way. Just think about any product where they are selling a half baked product, and repeatedly telling the user you are not using it properly.
If you buy a table saw and can't figure out how to cut a straight line in a piece of wood with it - or keep cutting your fingers off - but didn't take any time at all to learn how to use it, that's on you.
Likewise a car, you have to take lessons and a test before you can use those!
Why should LLMs be any different?