Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How I write software with LLMs

stavros.io

Post reply on HN
Print view View original

341–350 of 544 posts

Re: How I write software with LLMs

#341

Post by raw_anon_1111 »

datsci_est_2015 wrote: post #330
raw_anon_1111 wrote: post #299

Earlier quoted context omitted.

Do you know how every nail was put into your house? Does the general contractor?

I know where they fucked up and cost me thousands of dollars due to cutting corners during build-out and poor architectural decisions during planning. These kinds of things become very obvious during destructive inspection, which is probably why there are so many limitations on warranties; I digress. He’s mildly controversial, but watch some @cyfyhomeinspections on YouTube to get a good idea of what you can infer of…

So you’re saying that whether it’s humans or AI - when you delegate something to others you have no idea whether it’s producing quality without you checking yourself…

Re: How I write software with LLMs

#343

Post by gwbas1c »

> On the flip side, when I’m not familiar enough with the technology to be on top of the architecture, I tend to not catch bad decisions that the LLM makes. This leads to the LLM building more and more on top of those bad decisions, eventually getting in a state where it can’t untangle the mess. You know this happens when you keep telling the LLM the code doesn’t work, it says “I know why! Let me fix it” and keeps breaking things more and more.

That exact thing happens with people too! Specifically when a cheap entrepreneur hires a novice developer and can't give the developer appropriate mentoring and reviews.

Re: How I write software with LLMs

#344

Post by jmalicki »

petcat wrote: post #237
awakeasleep wrote: post #230

Earlier quoted context omitted.

Explain how fragility of implementation, like spaghetti code, high coupling low cohesion fit into your world view?

As human developers, I think we're struggling with "letting go" of the code. The code we write (or agents write) is really just an intermediate representation (IR) of the solution. For instance, GCC will inline functions, unroll loops, and myriad other optimizations that we don't care about (and actually want!). But when we review the ASM that GCC generates we are not concerned with the "spaghetti" and the "high coup…

I've actually found that well-written well-documented non-spaghetti code is even more important now that we have LLMs.

Why? Because LLMs can get easily confused, so they need well written code they can understand if the LLM is going to maintain the codebase it writes.

The cleaner I keep my codebase, and the better (not necessarily more) abstracted it is, the easier it is for the LLM to understand the code within its limited context window. Good abstractions help the right level of understanding fit within the context window, etc.

I would argue that use of LLMs change what good code is, since "good" now means you have to meaningfully fit good ideas in chunks of 125k tokens.

Re: How I write software with LLMs

#345

Post by throwaw12 »

raw_anon_1111 wrote: post #291
throwaw12 wrote: post #259

Earlier quoted context omitted.

Valid points. But crucial part of not "letting go" of the code is because we are responsible for that code at the moment. If, in the future, LLM providers will take ownership of our on-calls for the code they have produced, I would write "AUTO-REVIEW-ACCEPTER" bot to accept everything and deploy it to production. If, company requires me to own something, then I should be aware about what's that thing and understand i…

In the past ten years as a team lead/architect/person who was responsible for outsourced implementations (ie Salesforce/Workday integrations, etc), I’ve been responsible for a lot of code I didn’t write. What sense would it have made for me to review the code of the web front end of the web developer for best practices when I haven’t written a web app since 2002?

as a team lead, if you are not aware of what's happening in the team, what kind of team lead is this?

on the other hand, you may have been an engineering manager, who is responsible for the team, but a lot of times they do not participate in on-call rotations (only as last escalation)

Re: How I write software with LLMs

#346

Post by LogicFailsMe »

jplusequalt wrote: post #324
LogicFailsMe wrote: post #302

Earlier quoted context omitted.

Sounds like influencer nonsense to me. Touch grass. If the people are fed and housed, there's no collapse. And if the billionaire class lets them starve, they will finally go through some things just like the aristocracy in France once did. And I think even Peter Thiel is smarter than that. You can feed yourself for OTOH if what you're really talking about is the long-term collapse in our ludicrous carbon footprint w…

>You can feed yourself for You are the epitome of the tech bro.

Sure, sure. Understanding how these sociopaths think clearly makes me a tech bro rather than someone who incorporates worst-case scenarios into my planning. Suggesting they would maintain minimum viable society to save their own asses means I'm in favor of it, right? This is why I work remotely.

Re: How I write software with LLMs

#348

Post by raw_anon_1111 »

jmalicki wrote: post #344
petcat wrote: post #237

Earlier quoted context omitted.

As human developers, I think we're struggling with "letting go" of the code. The code we write (or agents write) is really just an intermediate representation (IR) of the solution. For instance, GCC will inline functions, unroll loops, and myriad other optimizations that we don't care about (and actually want!). But when we review the ASM that GCC generates we are not concerned with the "spaghetti" and the "high coup…

I've actually found that well-written well-documented non-spaghetti code is even more important now that we have LLMs. Why? Because LLMs can get easily confused, so they need well written code they can understand if the LLM is going to maintain the codebase it writes. The cleaner I keep my codebase, and the better (not necessarily more) abstracted it is, the easier it is for the LLM to understand the code within its…

I somewhat agree. But that’s more about modularity. It helps when I can just have Claude code focus on one folder with its own Claude file where it describes the invariants - the inputs and outputs.

Re: How I write software with LLMs

#349

Post by LogicFailsMe »

raw_anon_1111 wrote: post #325
jplusequalt wrote: post #320

Earlier quoted context omitted.

>If you can build things, AI coding agents will let you build faster and more for the same amount of effort. But you aren't building, your LLM is. Also, you are only thinking about ways as you, a supposed builder, will benefit from this technology. Have you considered how all previous waves of new technologies have introduced downstream effects that have muddied our societies? LLMs are not unique in this regard, and…

Would you say the general contractor for your home isn’t a builder because he didn’t install the toilets?

I think that's precisely his thinking and don't let him know about all those fancy expensive unitasker tools they have that you probably don't that let them do it far more cost effectively and better than the typical homeowner. Won't you think of the jerbs(tm)? And to Captain dystopia, life expectencies were increasing monotonically until COVID. Wonder what changed?

Re: How I write software with LLMs

#350

Post by stavros »

gwbas1c wrote: post #343

> On the flip side, when I’m not familiar enough with the technology to be on top of the architecture, I tend to not catch bad decisions that the LLM makes. This leads to the LLM building more and more on top of those bad decisions, eventually getting in a state where it can’t untangle the mess. You know this happens when you keep telling the LLM the code doesn’t work, it says “I know why! Let me fix it” and keeps br…

That's actually very true, I didn't realize. Huh, interesting, thanks.
Post reply on HN