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

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

#181

Post by helge9210 » Mon, Mar 23, 2026, 8:09 AM UTC

bluefirebrand wrote: post #160

jmull wrote: post #102

> or the boilerplate, libraries, build-tools, and refactoring If your dev group is spending 90% of their time on these... well, you'd probably be right to fire someone. Not most of the developers but whoever put in place a system where so much time is spent on overhead/retrograde activities. Something that's getting lost in the new, low cost of generating code is that code is a burden, not an asset. There's an ongoin…

> LLMs lower maintenance cost Even the most enthusiastic AI boosters I've read don't seem to agree with this. From what I can tell, LLMs are still mostly useful at building in greenfield projects, and they are weak at maintaining brownfield projects

From my experience greenfield /brownfield is not the best dichotomy here. I observed, how same tooling is generating meaningless slop on greenfield project and 10kLoC of change (leading to an outage) on existing project in one hands and building a fairly complex new project and fixing a long (years) standing bug with a two lines patch in the other.

And I have more examples, where I, personally, was on the both sides of the fence: defined by my level of the same problem understanding, not by the tooling.

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

#182

Post by Kiro » Mon, Mar 23, 2026, 8:18 AM UTC

maccard wrote: post #157

linsomniac wrote: post #142

Earlier quoted context omitted.

>Thats not my fault. I don't know that it's useful to assign blame here. It probably is to your benefit, if you are a coding professional, to understand why your results are so drastically different from what others are seeing. You started this thread saying "I keep getting told I'll be amazed at what it can do, but the tools keep failing at the first hurdle." I'm telling you that something is wrong, that is why you…

> 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.

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

#183

Post by maccard » Mon, Mar 23, 2026, 8:30 AM UTC

jmalicki wrote: post #103

jayd16 wrote: post #84

Earlier quoted context omitted.

You say it doesn't fail but you also mention all these work around you know and try...sounds like it fails a lot but your tolerance is different.

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.

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

#184

Post by maccard » Mon, Mar 23, 2026, 8:36 AM UTC

wrs wrote: post #165

maccard wrote: post #158

Earlier quoted context omitted.

I mean, I don’t know how much less scope I can give it. The next step is writing the 5 lines of code I want it to write. I also clearly said I didn’t allow it one output, I gave it the compile error message, it changed a different line, I told it it was at the affected line and to check the docs. Claude code then tried to query the DLL for the function, abandoned that and then did something else incorrect. I’m litera…

I understand (and don’t know what to say beyond “that’s weird”). I was just reacting to your equating “the first try sometimes doesn’t compile” with “it often fails”. That’s only a failure if you stop at that point.

In the first comment you’ll see that it didn’t compile, I prompted to fix it and eventually fixed it myself. When I asked it to proceed to the next task it blew away my fix and left it in a broken state.

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

#185

Post by maccard » Mon, Mar 23, 2026, 8:39 AM UTC

shireboy wrote: post #89

wrs wrote: post #75

Earlier quoted context omitted.

I’m honestly baffled by this. I don’t want to tell you “you’re holding it wrong” but if this is your normal experience there’s something weird happening. Friday afternoon I made a new directory and told Claude Code I wanted to make a Go proxy so I could have a request/callback HTTP API for a 3rd party service whose official API is only persistent websocket connections. I had it read the service’s API docs, engage in…

Similar. I regularly use Github copilot (with claude models sometimes) and it works amazingly. But I see some who struggle with them. I have sort of learned to talk to it, understand what it is generating, and routinely use to generate fixes, whole features, etc. much much faster than I could before.

I’ve found copilot to generate worse code, and the editor integrations to be unusable (lets insert this block of code at the wrong place in the file for example), but overall for it to do the right thing enough that I can patch it. I’ve found Claude code just goes mad and gets stuck in a loop and I need to pull it out and figure out where in the hundreds of lines of code it’s generates in the last few minutes it’s gone so wrong.

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

#186

Post by sdn90 » Mon, Mar 23, 2026, 9:18 AM UTC

I think we are in a price discovery phase overall for human labor.

Just like financial markets, this phase is very volatile. But today’s price can look much different in 1, 2, 5, and 10 years.

Right now there’s a lot of opportunity to disrupt companies who are moving much slower since adoption can vary greatly.

But I think in a few years this meta will be overcrowded. The overall skill/productivity gap across companies will be reduced and the bar for productivity will be raised.

There’s room for taking profits now from the productivity gains but I don’t think it will last long.

If AI is really increasing productivity enough to reduce headcount right now, it won’t be in future. If all your competitors are using AI as effectively as you are, can you still do this?

The world’s demand for productivity is limitless. As of right now you still need someone to at least install Claude Code and run the binary.

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

#187

Post by d--b » Mon, Mar 23, 2026, 9:51 AM UTC

Definitely better products.

The main effect is that you build things a lot faster.

The secondary effect is that, since you can code a lot faster, you are no longer scared of large refactors, ports to other languages, and all that kind of tedious stuff.

That means that if you design something, ship it, and realize it's bad, you can completely change it.

The "oh we should have done it differently, but now it would take years to change, so we have to deal with legacy garbage" argument does really make sense anymore.

Like if HN had LLM agents, we wouldn't have had to wait for years for them to solve the "click here for more comments" problem. And iterating with users is a lot faster.

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

#188

Post by muzani » Mon, Mar 23, 2026, 10:16 AM UTC

hirako2000 wrote: post #67

muzani wrote: post #17

Earlier quoted context omitted.

In companies like the oil industry, doubling productivity would mean reducing the expected life span. Costs tend to catch up with profits, especially due to taxes. Layoffs happen inevitably. Is it the same with tech? Facebook has 3 billion monthly active users. No amount of tech will bring that up to 6 billion. If you were to double the amount of time someone spends on Facebook, or double the ads they see or double t…

That's assuming a company is constrained, to not expand its portfolio. Taking the example of Facebook. They are in social media, messaging, AI, VR/AR hardware and software, a few other things, meta universe whatever that was, now left with the name. Facebook isn't delivering or successful on all its ventures, it knows that, it keeps investing in other segments. More productivity would mean at least diversifying, they…

There's diminishing gains to some features too. Facebook added Dating but according to a friend who worked on it, the increased privacy restrictions developed in parallel elsewhere killed the algorithm. It died on launch, and wasn't even their fault.

Even if it succeeded, having more buttons everywhere - marketplace, reels, stories, blogs, articles, groups, etc. A lot of this make the whole experience more crowded.

Productivity here has an odd effect, sort of like larger roads causing more traffic jams.

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

#189

Post by jmalicki » Mon, Mar 23, 2026, 10:19 AM UTC

senordevnyc wrote: post #129

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 so perplexing to me. I've definitely hit these kinds of issues (which usually result in me cursing at the agent in all caps while telling it to get its shit together!), but it's almost always a long ways into a session where I know context rot is an issue, and the assumption it's making is a dumb one but it's also in the middle of a complex task...I just haven't had anything remotely like the situation you're…

It's been awhile, but I once spent four hours trying to get Opus 4.1 to change the color palette of a bar graph, that would've taken me 5 minutes.

The only reason I wasted so much time was that given all of my other positive experiences, clearly I must have been prompting it incorrectly, and I should learn how to fix it.

After blowing four hours I just changed the colors by hand. I took away that it's almost completely unpredictable what will be easy and what will be hard for an LLM.

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

#190

Post by maccard » Mon, Mar 23, 2026, 10:49 AM UTC

linsomniac wrote: post #120

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…

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. The agentic loop came up with a plan, claimed it was done, but _didn't execute the verifiaction it told me it was going to execute_.

[0] https://gist.github.com/donalmacc/e91955be9792a983c375a098ba...