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

Ask HN: AI productivity gains – do you fire devs or build better products?

news.ycombinator.com

Post reply on HN
Print view View original

191–200 of 244 posts

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#191

Post by maccard »

wrs wrote: post #174
maccard wrote: post #157

Earlier quoted context omitted.

> I don’t know that it’s useful to assign blame here Oh - I’m blaming Claude not anyone else. I’ve tried again this evening and the same prompt (in the same directory on the same project) worked. > i don’t know if you’re using an ancient version of Claude code, I’m on a version from some time last week, and using opus 4.6 > This is why a lot of people are saying "you'll be amazed at what it can do", and it points to…

I assure you I would have noticed if the result of my Friday effort was something that didn't compile, rather than a service that seems to work just fine. I've reviewed about half the code so far and it seems quite reasonable. For some reason I'm getting downvoted for trying to help, but regardless, if you can (and want to) post a transcript somewhere of some of these sessions that aren't working out, maybe some of u…

https://news.ycombinator.com/item?id=47487638

Fresh prompt in a codebase with a claude.md I asked it to do a simple task. I've shared the prompt, plan, output in the linked gist.

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#192

Post by maleldil »

maccard wrote: post #183
jmalicki wrote: post #103

Earlier quoted context omitted.

Most people I've seen complain say things like "I asked it for code and it didn't compile." The real magic of LLMs comes when they iterate until completion until the code compiles and the test passes, and you don't even bother looking at it until then. Each step is pretty stupid, but the ability to very quickly doggedly keep at it until success quite often produces great work. If you don't have linters that are check…

> The real magic of LLMs comes when they iterate until completion until the code compiles and the test passes, and you don't even bother looking at it until then. If you read my post, you’d see that Claude code didn’t do that, I had to intervene in the agent loop and when I did it undid my fixes.

This is not compatible with many people's experiences. I use Python with a type checker. I tell Claude that the task is only complete once the type checker passes cleanly. It doesn't stop until there are no type errors. This should be even easier in a compiled language, especially if you also tell it to run the tests.

In fact, I find that with a strict feedback loop set up (i.e. a lot of lint rules, a strict type checker and fast unit tests), it will almost always generate what I want.

As someone else said, each step might be pretty stupid, but if you have a fast iteration loop, it can run until everything passes cleanly. My recommendation is to specify what really counts as "done" in your AGENTS.md/CLAUDE.md.

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#194

Post by maccard »

Kiro wrote: post #182
maccard wrote: post #157

Earlier quoted context omitted.

> I don’t know that it’s useful to assign blame here Oh - I’m blaming Claude not anyone else. I’ve tried again this evening and the same prompt (in the same directory on the same project) worked. > i don’t know if you’re using an ancient version of Claude code, I’m on a version from some time last week, and using opus 4.6 > This is why a lot of people are saying "you'll be amazed at what it can do", and it points to…

I understand that you think you are arguing that the models are bad, but the only thing people wonder is what you're doing to fail so spectacularly and whether you're actually being truthful.

And I’m wondering the same thing. The people replying to me are saying “your experience must be wrong/you must be doing something wrong” and then 1-2 threads later they say “well yeah it doesn’t do X but if I do Y and Z it works”, which… kind of proves the point?

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#195

Post by maccard »

maleldil wrote: post #192
maccard wrote: post #183

Earlier quoted context omitted.

> The real magic of LLMs comes when they iterate until completion until the code compiles and the test passes, and you don't even bother looking at it until then. If you read my post, you’d see that Claude code didn’t do that, I had to intervene in the agent loop and when I did it undid my fixes.

This is not compatible with many people's experiences. I use Python with a type checker. I tell Claude that the task is only complete once the type checker passes cleanly. It doesn't stop until there are no type errors. This should be even easier in a compiled language, especially if you also tell it to run the tests. In fact, I find that with a strict feedback loop set up (i.e. a lot of lint rules, a strict type che…

I tried again this morning - https://news.ycombinator.com/item?id=47487638 another hard failure that Claude code says passed.

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#196

Post by pydry »

lugu wrote: post #145
roncesvalles wrote: post #83

Earlier quoted context omitted.

The analogy of thinking of coding AI like it's chess AI is terrible. If chess AI was at the level of coding AI, it wouldn't win a single game. This kind of thinking is actually a big reason why execs are being misinformed into overestimating LLM abilities. LLM coding agents alone are not good enough to replace any single developer. They only make a developer x% faster. That dev who is now x% faster may then allow you…

I like the chess analogy as it answer the question: why can't i see those gain? To adress your point, let's try another one analogy. Imagine secreterial assistants, discussing their risk of been replaced by computers in the 80s. They would think: someone still need to type those letters, sit next to that phone and make those appointments, I am safe. Computers won't replace me. It is not that AI will do all of your ta…

I imagine if they tried to replace typists with keyboards that produced plausible looking words that were entirely wrong half the time then we'd probably still have plenty of typists.

I tend to find that the volume of automation predictions inversely correlates to how real they are.

When capitalists actually have the automation tech they dont shout about it they just do it quietly and collect the profits.

When, say, Bezos is worried about his unionizing workforce and wants to intimidate - that's when the hot takes and splashy media articles about billions invested in automation "coming for yer jerb" you read about get published.

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#197

Post by prettyblocks »

maccard wrote: post #61

> try it, you might actually be amazed. I keep being told this and the tools keep falling at the first hurdle. This morning I asked Claude to use a library to load a toml file in .net and print a value. It immediately explained how it was an easy file format to parse and didn’t need a library. I undid, went back to plan mode and it picked a library, added it and claimed it was done. Except the code didn’t compile. Th…

I think good results come from spending a substantial amount of time reading the claude-code documentation and setting up an environment that lets you work in this new paradigm. Asking it a few things, getting poor results, and deciding "it doesn't work when you ask it to correct itself won't get you that far.

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#199

Post by sigbottle »

krastanov wrote: post #66
maccard wrote: post #61

> try it, you might actually be amazed. I keep being told this and the tools keep falling at the first hurdle. This morning I asked Claude to use a library to load a toml file in .net and print a value. It immediately explained how it was an easy file format to parse and didn’t need a library. I undid, went back to plan mode and it picked a library, added it and claimed it was done. Except the code didn’t compile. Th…

This is fascinating to me. I completely believe you and I will not bother you with all the common "but did you try to tell it this or that" responses, but this is such a different experience from mine. I did the exact same task with claude in the Julia language last week, and everything worked perfectly. I am now in the habit of adding "keep it simple, use only public interfaces, do not use internals, be elegant and…

Idk. Had a friend recommend me gsdv2 and I wasted like 100$ + so much time trying to debug said crap. I went back to codex and it 1 shot my problems easily.

And this was from two people who were 100% aligned on agentic AI coding. I've been using AI for years now and agentic AI for several months now. I was told that I bring out the worst in LLMs. Except... I was able to achieve better results, WITH LLMs, on OTHER frameworks. So like, ?

It may be easier to draw the boundary between "AI and non AI users", but as AI becomes prolific, the us vs them angle that people keep using won't apply anymore.

The age old "user versus tool" debate goes on, but it seems like gaslighting is popular these days. I classify it as gaslighting because I'm clearly a falsifiable test case, I'm even gung ho for LLMs, yet any kind of dissent is immediately warped into user error. It doesn't matter what you say or where you are on the spectrum, if you have 1 bad experience and speak up about it it's an issue. Guess that's not really an issue for the human condition though.

Re: Ask HN: AI productivity gains – do you fire devs or build better products?

#200

Post by saulpw »

maccard wrote: post #159
saulpw wrote: post #151

Earlier quoted context omitted.

It's not unusual for my initial output (as a programmer) not to compile either. I wouldn't say I "failed" if I can then get it to compile. Which as people are saying, is what happens with Claude Code and Opus, either automatically or at most when I say "get it to compile".

But when it doesn’t compile for me, I don’t claim it’s finished.

Something is really wrong with your setup and I can't tell what it is from these high-level descriptions. Would you be willing to hop on a videochat and walk through this simple case? I'd be really curious to figure out what's going on, it's pretty atypical.
Post reply on HN