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

Eight years of wanting, three months of building with AI

lalitm.com

Post reply on HN
Print view View original

301–310 of 349 posts

Re: Eight years of wanting, three months of building with AI

#301

Post by deadbabe »

JoelJacobson wrote: post #257
deadbabe wrote: post #242

Earlier quoted context omitted.

LISTEN/NOTIFY is not brittle, we use it for millions of events per day.

I agree! It should be very stable, IMO. If not, then please send a bug report and we'll look into it. Also, now it scales well with the number of listening connections (given clients listen on unique channel names): https://git.postgresql.org/gitweb/?p=postgresql.git;a=commit...

The LISTEN/NOTIFY feature really just doesn’t get enough PR. It is perfectly suitable for production workloads yet people still want to reach for more complicated solutions they don’t need.

Re: Eight years of wanting, three months of building with AI

#302

Post by figassis »

deadbabe wrote: post #242
figassis wrote: post #91

Earlier quoted context omitted.

My process: start ideating and get the AI to poke holes in your reasoning, your vision, scalability, etc. do this for a few days while taking breaks. This is all contained in one Md file with mermaid diagrams and sections. Then use ideation to architect, dive into details and tell the AI exactly what your choices are, how certain methods should be called, how logging and observability should be setup, what language t…

LISTEN/NOTIFY is not brittle, we use it for millions of events per day.

It's not the feature itself, it's how/what the llm tries to use it for. It uses it to cross any and all architectural boundaries.

Re: Eight years of wanting, three months of building with AI

#303

Post by devmor »

avadodin wrote: post #206
devmor wrote: post #199

Earlier quoted context omitted.

Copilot isn’t really a competing product to Claude - in fact I use Claude through copilot. I have found in general that for the type of work I do (senior to staff level engineering, 90-10 research to programming) that Claude Opus is the only model really worth my time - but I just really like the Copilot CLI tooling.

So, are you using it for the 10%? I do use LLMs to learn about new subjects but we already only bill 10% for "coding" and that's inflating it to cover other parts. I can't imagine that slopping it up would be a great decision. Having alien code that no one ever understood between a bug report and a solution. Anthropic isn't going to give us money for our lost contracts, is it?

I would say I'm using it for about half of the "10%" and and a quarter of the "90%".

> I can't imagine that slopping it up would be a great decision. Having alien code that no one ever understood between a bug report and a solution. Anthropic isn't going to give us money for our lost contracts, is it?

Absolutely, that's a real concern. The only time I will let it loose on something is a throwaway project to test something, or a small tool that I know I can write deterministic tests for.

On codebases of any significant size, I'm using it more like a custom domain Stackoverflow search engine.

Re: Eight years of wanting, three months of building with AI

#304

Post by devmor »

eszed wrote: post #256
devmor wrote: post #142

Earlier quoted context omitted.

I think you’re handwaving away vague, ungrounded intuition and calling it learning. For instance, if I say “I noticed I run better in my blue shoes than my red shoes” I did not learn anything. If I examine my shoes and notice that my blue shoes have a cushioned sole, while my red shoes are flat, I can combine that with thinking about how I run and learn that cushioned soles cause less fatigue to the muscles in my fee…

You're always free to stop at the level of abstraction at which you find a certain answer to be satisfying, but you can also keep digging. Why are flat shoes better? Well, it's to do with my gait. Ok, but why is my gait like that? Something-something musculoskeletal. Why is my body that way? Something-something genetic. OK, but why is that? And so on. Pursued far enough, any line of thought will reach something non-d…

It is very silly to treat zero grounding the same as accepting core, proven concepts. Your PoV here is no different than saying "It rains because god is sad and crying" is an appropriate thing to believe.

If you want to say "god is responsible for creating the precipitation cycle", sure. But we don't disregard understanding that exists to substitute intuition.

Re: Eight years of wanting, three months of building with AI

#305

Post by 9rx »

darkstarsys wrote: post #297
9rx wrote: post #252

Earlier quoted context omitted.

Yeah, I've found LLMs cannot write good Typescript code period. The good news is that they are excellent at some other languages.

I can't agree here. https://pelorus-nav.com/ (one of my side projects) is 95-98% written by Claude Opus 4.6, all in very nice typescript which I carefully review and correct, and use good prompting and context hygiene to ensure it doesn't take shortcuts. It's taken a month or so but so worth it. And my packing list app packzen.org is also pretty decent typescript all through.

> which I carefully review and correct

So you do agree? If you are having to review and correct then it's not really the LLM writing it anymore. I have little doubt that you can write good Typescript, but that's not what I said. I said LLMs cannot write good Typescript and it seems you agree given your purported actions towards it. Which is quite unlike some other languages where LLMs write good code all the time — no hand holding necessary.

Re: Eight years of wanting, three months of building with AI

#306

Post by 9rx »

camdenreslink wrote: post #300
9rx wrote: post #252

Earlier quoted context omitted.

Yeah, I've found LLMs cannot write good Typescript code period. The good news is that they are excellent at some other languages.

I think it can write working TypeScript code, and it can write good TypeScript code if it is guided by a knowledgable programmer. It requires actually reviewing all the code and giving pointed feedback though (which at that point is only slightly more efficient than just writing it yourself).

> It requires actually reviewing all the code and giving pointed feedback though

Exactly. You can write good Typescript, no doubt, but LLMs cannot. This is not like some other languages where LLM generated code is actually consistently good without needing to become the author.

Re: Eight years of wanting, three months of building with AI

#307

Post by duggan »

lowsong wrote: post #279
duggan wrote: post #264

Earlier quoted context omitted.

> $200/month is already out of reach of the majority of the population. 1. You can build small applications with the $20/month sub, much more with the $100/month. Competition and technology improvements will inevitably improve the price to value ratio. 2. Cable sports subscriptions are in a similar price range. Expensive, but not exclusive to “the elites”.

The median per capita income in the United States is $37,683/year.[0] Depending on your state, after taxes, that's something like ~$2,600/month. You're asking almost 10% of their post-tax income to this just for the opportunity to create software. With rent, food, and other living expenses many households at that income level simply cannot afford this. This is the median income. If it's a struggle for someone on this…

The bar for "create software" up to this last year or so was "learn software development" or "pay someone else".

Personally, I think millions more people having the ability to create some subset of software is an incredible shift.

Re: Eight years of wanting, three months of building with AI

#308

Post by lowsong »

baggy_trough wrote: post #299
lowsong wrote: post #203

Earlier quoted context omitted.

> I don't know what to say to you. More people are coding now with AI than ever coded before. If your argument was true, then that would just mean that there are more elites than ever. Obviously that's not what's happening. I don't know how I can explain this any more clearly. If you need AI to create software, and the cost of AI is $200/month, then only people who can afford $200/month can create software. Costs wil…

> $200/month is already out of reach of the majority of the population. Increases from here means only a small percentage of the richest people can afford it. This is an absurd claim. There are many things the majority of the population spends money on that cost more than this.

I'm going to take your comment at face value, and I'm also going to assume that you're US-based.

You need to take a step back and look at the economic reality of the majority of Americans today. Many live paycheck-to-paycheck, even those with "middle class" incomes. For many a $200 one-off bill is debilitating, yet alone a recurring subscription. If you don't know that, you have a dangerously narrow view of the economy.

Re: Eight years of wanting, three months of building with AI

#309

Post by simondotau »

lyricalstring wrote: post #272
simondotau wrote: post #6

This essay perfectly encapsulates my own experience. My biggest frustration is that the AI is astonishingly good at making awful slop which somehow works. It’s got no taste, no concern for elegance, no eagerness for the satisfyingly terse. My job has shifted from code writer to quality control officer. Nowhere is this more obvious in my current projects than with CRUD interface building. It will go nuts building thes…

This is the thing that gets me. The code compiles. Passes tests. So you stop reading it. Why wouldn't you. Then three weeks later you're tracing some control flow that makes no sense and nobody knows why it's structured that way. Not you, not the model. I've been treating it like code from a contractor now, review every line same as a junior dev's PR. Gets tedious but the alternative is worse.

I’ve been treating it like a glorified autocomplete, or a glorified search and replace. Everything else is saxophone jazz when I’m writing for a string quartet: useful for inspiration, useful for understanding what isn’t clearly explained, sometimes it builds a decent first attempt, occasionally it gets shockingly close, but I’ve learned to never let my guard down. Go too far and untangling its slop becomes burdensome. Leave it to its own devices for more than a few rounds and it can become so unfixable it’s easier to start from scratch.

Re: Eight years of wanting, three months of building with AI

#310

Post by hypersolo »

throwatdem12311 wrote: post #100
Aurornis wrote: post #10

Refreshing to see an honest and balanced take on AI coding. This is what real AI-assisted coding looks like once you get past the initial wow factor of having the AI write code that executes and does what you asked. This experience is familiar to every serious software engineer who has used AI code gen and then reviewed the output: > But when I reviewed the codebase in detail in late January, the downside was obvious…

For me it’s just a matter of “does this actually save me time at all?” If it generates the slop version in a week but it takes me 3 more weeks to clean it up, could I have I just done it right the first time myself in 4 weeks instead? How much money have I wasted in tokens?

[flagged]
Post reply on HN