The reliance on “IMPORTANT” and “NEVER” tags feels like a necessary evil that points to current model limitations. It works, but it’s not elegant. I’m curious how this will evolve as models become more steerable.
What makes Claude Code so damn good
291–300 of 322 posts
Re: What makes Claude Code so damn good
#292Earlier quoted context omitted.
I generally work as openly as possible on github, and I am deliberately avoiding manual coding for a while to try to learn these (infuriating/wonderful) tools more thoroughly. Unfortunately I can't always share all of my work, but everything on github after perhaps 2025-06-01 is as vibe-coded as I can get it to be. (I manually review commits before they're pushed, and PRs once in a complete state, but I always feed t…
Everyone wants to see your very profitable startup, it’s simply free advertising. Why not share it?
I definitely don't have a very profitable startup. I'm simply a working programmer trying to learn new tools.
Re: What makes Claude Code so damn good
#293Earlier quoted context omitted.
mind typing this up? i've got a basic GPT -> Claude workflow going for now
https://gist.github.com/githubcustomerserviceistrash/c716e76... I should mention I made that one for my research/stats workflow, so there's some specific stuff in there for that, but you can prompt chat gpt to generalize it.
I mean, damn. Are terms like “executable oracles” and “hermetic boots” related to your domain, or are you using these as terms of art for an agent? Oracle being a source of truth, hermetic meaning no external dependencies or side effects - definitions in furtherance of your request for concise language. Would love to understand more.
Re: What makes Claude Code so damn good
#294Earlier quoted context omitted.
We get it; it helped you build a bunch of stuff. Why not just post your company?
We're in the govtech x AI space (building software for local governments and government-adjacent customers). I don't feel comfortable linking my direct startup yet - it serves me no benefit here (I just get judged by a bunch of angry programmers) and we're in the middle of fundraising with investors.
Then why bring it up in the first place if you’re not even willing to show one shred of evidence of your vibe coding output, even a link to you companies landing page?
Re: What makes Claude Code so damn good
#295Earlier quoted context omitted.
HN is by no means "pro-AI". It's sharply divided, and (as always with these things) each side assumes the other side is dominant.
"After viewing identical samples of major network television coverage of the Beirut massacre, both pro-Israeli and pro-Arab partisans rated these programs, and those responsible for them, as being biased against their side." https://users.ssc.wisc.edu/~jpiliavi/965/hwang.pdf
No post body was provided.
Re: What makes Claude Code so damn good
#296We’re considering building a coding agent for Lowdefy[1], a framework that lets you build web apps with YAML config. For those who’ve built coding agents: do you think LLMs are better suited for generating structured config vs. raw code? My theory is that agents producing valid YAML/JSON schemas could be more reliable than code generation. The output is constrained, easier to validate, and when it breaks, you can act…
> For those who’ve built coding agents: do you think LLMs are better suited for generating structured config vs. raw code?
Raw code. Use case was configuring a mapping of health data JSON from heterogeneous sources to a standard (also JSON) format. Initial prototype was a YAML DSL, based on the same theory as yours. LLMs had difficulty using the DSL’s semantics correctly, or even getting its syntax (not YAML-level syntax, but the schema: nesting levels for different constructs, and so on). It’s possible that better error loops or something would have cracked it, but a second prototype generating jq worked so much better out of the box that we basically never looked back.
Re: What makes Claude Code so damn good
#297Earlier quoted context omitted.
> I've literally built the entire MVP of my startup on Claude Code and now have paying customers. Would you mind linking to your startup? I’m genuinely curious to see it. (I won’t reply back with opinions about it. I just want to know what people are actually building with these tools!)
My github has examples of work I've done recently that are open source. I'm deliberately trying not to do too much manual coding right now so I can figure out these (infuriating/wonderful) tools.
Thanks, I’ll take a look. Everyone uses these tools differently, so I find AI-generated repos (and AI live-coding streams) to be useful learning material.
FWIW: “Infuriating/wonderful” is exactly how I feel about LLM copilots, too! Like you, I also use them extensively. But nothing I’ve built (yet?) has crossed the threshold into salable web services and every time someone makes the claim that they’ve primarily used AI to launch a new business with paid customers, links are curiously absent from the discussion… too bad, since they’d be great learning material too!
Re: What makes Claude Code so damn good
#298> The main takeaway, again, is to keep things simple. if true this seems like a bloated approach but tbh I wouldn't claim to know totally how to use Claude like the author here... I find you can get a lot of mileage out of "regular" prompts, I'd call them? Just asking for what you need one prompt at a time? I still can't visualize how any of the complexity on top of that like discussed in the article adds anything to…
How you see and use it is the same way I do. So interested to hear other replies
thanks, that's helpful to hear
I know this is a new "space" so I've just been going off what I can find on here and other places and...
it all seems a little confusing to me besides what I otherwise tried to describe (and which apparently resonates with you, which is good to see)
Re: What makes Claude Code so damn good
#299Earlier quoted context omitted.
[flagged]
Congratulations, you replace my pile of "slop" (which really is functional, tight code written by AI in 1/1000th of the time it would take me to write it) with your "shorter" code that has the exact same functionality and performance. Congrats? The reality is no one (except in the case of like competitive programming) cares about the length of your code so long as it's maintainable.
But that's the thing -- because I WROTE my code, I know there's nothing bizarre in it. Your code is almost guaranteed to have something bizarre and unexpected in it, at least somewhere.
Re: What makes Claude Code so damn good
#300Earlier quoted context omitted.
My github has examples of work I've done recently that are open source. I'm deliberately trying not to do too much manual coding right now so I can figure out these (infuriating/wonderful) tools.
Thanks, I’ll take a look. Everyone uses these tools differently, so I find AI-generated repos (and AI live-coding streams) to be useful learning material. FWIW: “Infuriating/wonderful” is exactly how I feel about LLM copilots, too! Like you, I also use them extensively. But nothing I’ve built (yet?) has crossed the threshold into salable web services and every time someone makes the claim that they’ve primarily used…
I will have one for you, most likely, later this week! Fingers crossed anyway!