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

201–210 of 244 posts

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

#201

Post by cadamsdotcom »

elvis10ten wrote: post #62
epicureanideal wrote: post #55

Earlier quoted context omitted.

And for a lot of AI transformation tasks, for a long time I've been using even clever regex search/replace, and with a few minutes of small adjustment afterward I have a 100% deterministic (or 95% deterministic and 5% manually human reviewed and edited) process for transforming code. Although of course I haven't tried that cross-language, etc. And of course, we didn't see a massive layoff after the introduction of sa…

I just had a relevant experience. I asked Claude to add “trace(‘$FunctionName’) {}” to all Composable functions in my app. Claude spent some time doing something. In between, I was like shoot, I could just do a deterministic regex match and replace.

Ask Claude to do that deterministic search & replace. Best of both worlds, and now you’re prompt engineering :)

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

#202

Post by wrs »

maccard wrote: post #190
linsomniac wrote: post #120

Earlier quoted context omitted.

My friend, with all due respect, I don't think this is a problem with the AI. I don't know anything about DotNet, but I just fired up Claude Code in an empty directory and asked it to create an example dotnet program using the Tomlyn library, it chugged away and ~5 minutes later I did a "grep Deserialize *" in the project and it came up with exactly the line you wanted (in your comment here) it to produce: var model…

I'm in claude code right now, with opus 4.6. Here [0] is my prompt, plan and result. When I prompted, it went spelunking in the parent folder for a bunch of stuff, which I interrupted and told it to focus on its current folder. It came up with a sensible plan, which I let it execute. I then switched to a new tab and ran `dotnet run publishing/publish.cs` - like claude says. And the script fails at the first hurdle. T…

When CC says "Verification" at the end like that, it means it's assuming you will do the verification. But you can tell it to do it (just say "verify it yourself" or something), and then (if needed) ask it to fix the errors, etc. You could even say "verify and fix errors until it works".

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

#203

Post by wrs »

maccard wrote: post #191
wrs wrote: post #174

Earlier quoted context omitted.

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.

OK, that was an extremely short interaction -- which may be the problem. I left a comment with suggestions.

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

#204

Post by lukev »

ThrowawayR2 wrote: post #27
lukev wrote: post #24

Earlier quoted context omitted.

I agree, but absence of evidence is not evidence of absence, and we currently have a lot of developers who feel very productive right now. We are very much in need of an actual way to measure real economic impact of AI-assisted coding, over both shorter and longer time horizons. There's been an absolute rash of vibecoded startups. Are we seeing better success rates or sales across the industry?

> " absence of evidence is not evidence of absence " That's the same false argument that the religious have offered for their beliefs and was debunked by Bertrand Russell's teapot argument: https://en.wikipedia.org/wiki/Russell%27s_teapot

I'm not speaking of burdens of proof about unfalsifiable statements.

I'm saying that I think this is an important enough question that I think we should seek real evidence in either direction, especially since apparently everyone already has a strong opinion (warranted or not.)

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

#205

Post by lordkrandel »

hermannj314 wrote: post #69
pydry wrote: post #21

Earlier quoted context omitted.

It's interesting that the people IRL I encounter who "get the most value" tend to be the devs who couldnt distinguish well written code from slop in the first place. People online with identical views to them all assure me that theyre all highly skilled though. Meanwhile I've been experimenting using AI for shopping and all of them so far are horrendous. Cant handle basic queries without tripping over themselves.

If you are a 2600 chess player, a bot that plays 1800 chess is a horrendous chess player. But you can understand why all the 1700 and below chess players say it is good and it is making them better using it for eval? Don't worry, AI will replace you one day, you are just smarter than most of us so you don't see it yet.

The thing is, AI is playing "tech chess" wonderful the first two moves, and then starts turning pieces around without much care, letting the queen die for no reason, but well, what a wonderful opening.

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

#206

Post by lordkrandel »

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…

If it worked, I would agree. AI just helped me finding bugs in some hashing function today, ok, nice. But only after 3 hours I got any result out of it, with 13 years of experience. My feeling is that newbies are creating todo lists with react , just like it has been copied from someone's tutorial they didnt bother to read before, and now they feel powerful. But hey, let them do our taxes then! And they get screwed in 0 seconds.

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

#207

Post by lordkrandel »

alexjplant wrote: post #44
lordkrandel wrote: post #4

Why do people keep ralking about AI as it actually worked? I still don't see ANY proof that it doesn't generate a total unmaintainable unsecure mess, that since you didn't develop, you don't know how to fix. Like running a F1 Ferrari on a countryside road: useless and dangerous

> Why do people keep ralking about AI as it actually worked? Because it does. > I still don't see ANY proof that it doesn't generate a total unmaintainable unsecure mess, that since you didn't develop, you don't know how to fix. I wouldn't know since it's been years since I've tried but I'd imagine that Claude Code would indeed generate a half-baked Next.js monstrosity if one-shot and left to its own devices. Being t…

> can give it a list of fields with validation rules and query patterns and it'll build me CRUD pages in a fraction of the time it'd take me to do so.

Ah, is this what you do for a job? I actually have to accord accounting rules between countries, evaluate different conflicting laws, understand what the government wants in a report, check that everything sums up... But if my job was CRUD apps and thats it, yes I would fear for my job.

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

#208

Post by lordkrandel »

deaux wrote: post #32
dominotw wrote: post #14

Earlier quoted context omitted.

so where are these one man products lauched in a month? not talking about toys or vibecoded crap no one uses.

They're here, I made one. Not a toy or vibecoded crap, people got immediate value. Not planning to doxx myself by linking it. This was more than a year ago when models weren't even as good yet. A year later it has thousands of consistent monthly users, and it only keeps growing. It's nothing compared to VC startups but for a solo dev, made in a month? Again, it's not a toy, it offers new functionality that simply did…

Blah blah blah

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

#209

Post by lordkrandel »

thefounder wrote: post #11
lordkrandel wrote: post #4

Why do people keep ralking about AI as it actually worked? I still don't see ANY proof that it doesn't generate a total unmaintainable unsecure mess, that since you didn't develop, you don't know how to fix. Like running a F1 Ferrari on a countryside road: useless and dangerous

You can launch a new product in one month instead of 12 months. I think this works best for startups where the risk tolerance is high but works less than ideal for companies such Amazon where system failure has high costs

Most startups fail because of no market or money issues, not because of product issues. You can build a wonderful cathedral and pray an empty god in a wonderful desert. Then someone cuts oil supply and the cathedral is not aor conditioned anymore. So go ahead, build 50 products, hope that 1 succeeds. My bet is that 50 will fail and 1 person in 1000 will succeed. But everyone will spend so much money on Nvidia and Anthropic that they will eradicate whatever else is in the world.

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

#210

Post by lordkrandel »

UqWBcuFx6NV4r wrote: post #42
lordkrandel wrote: post #4

Why do people keep ralking about AI as it actually worked? I still don't see ANY proof that it doesn't generate a total unmaintainable unsecure mess, that since you didn't develop, you don't know how to fix. Like running a F1 Ferrari on a countryside road: useless and dangerous

Person that can’t use a hammer “hasn’t seen any proof” that hammers work.

I definitely can use a hammer, trust me xD you're just bar chatter trying to belittle me, maybe, but do you actually know me, brah
Post reply on HN