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

Writing code is cheap now

simonwillison.net

Post reply on HN
Print view View original

471–480 of 522 posts

Re: Writing code is cheap now

#471

Post by signatoremo »

skydhash wrote: post #356
nthj wrote: post #353

Earlier quoted context omitted.

We didn’t fire all our developers when we invented compilers either, and for much the same reason we didn’t stop hiring laborers when we first built ships and established overseas trade routes: business will always expand to meet its reach Many enterprises are currently exploring to see if they can invite developers to leverage AI tools—like they leveraged the compiler—to be more productive. To operate on a higher pl…

> Many enterprises are currently exploring to see if they can invite developers to leverage AI tools—like they leveraged the compiler—to be more productive. To operate on a higher plane of agency, collaborating on what we should be building and not just technical execution. The thing is, developers have been hired to automate process, and as for any professional doing a good job, that means the output should perform…

> But now they are forcing us to use a tools that everyone knows is not reliable, but the onus is still on us to keep the same reliability. So do you see why we are not thrilled?

Why generalizing your own experience on other's?

Re: Writing code is cheap now

#472

Post by LtWorf »

simonw wrote: post #435
LtWorf wrote: post #433

Earlier quoted context omitted.

In what world is an LLM generating text faster than you can type? They are certainly slower than me at text generation.

Wow you must be fast at typing! Can you beat this one? https://chatjimmy.ai/ (It is to be fair running a pretty trash model, a quantized Llama 3.1 8B from ~18 months ago)

if I type nonsense like that thing, sure.

Re: Writing code is cheap now

#473

Post by neilwilson »

jimbokun wrote: post #453
neilwilson wrote: post #318

Earlier quoted context omitted.

Once writing code is cheap you don't maintain code. You regenerate it from scratch. What you maintain is the specification harness, and change that to change the code. We have to start thinking at a higher level, and see code generation in the same way we currently see compilation.

Tokens aren’t free. Far more expensive than compilation and non deterministic so you’re not sure if you will get the same software if you give the AI the same spec.

You'll get the same software in outcome terms. Which is what we want.

Tokens are cheaper than getting an individual to modify the code, and likely the tokens will get cheaper - in the same way compilation has (which used to be batched once a day overnight in the mainframe era).

Non-determinism is how the whole LLM system works. All we're doing with agents is adding another layer of reinforcement learning that gets it to converge on the correct output.

That's also how routing protocols like OSPF work. There's no guarantee when those multicast packets will turn up, yet the routes converge and networks stay stable.

I think this fear of non-determinism needs to pass, but it will only pass if evidence of success arises.

Re: Writing code is cheap now

#474

Post by neilwilson »

simonw wrote: post #321
neilwilson wrote: post #318

Earlier quoted context omitted.

Once writing code is cheap you don't maintain code. You regenerate it from scratch. What you maintain is the specification harness, and change that to change the code. We have to start thinking at a higher level, and see code generation in the same way we currently see compilation.

I'm not sold on that idea yet. I don't just have LLMs spit out code. I have them spit out code and then I try that code out myself - sometimes via reviewing it and automated tests, sometimes just by using it and confirming it does the right thing. That upgrades the code to a status of generated and verified . That's a lot more valuable than code that's just generated but hasn't been verified. If I throw it all away e…

I suspect that is where we will be going next - automated verification. At least to the point where we can pass it over the wall for user acceptance testing.

Is it possible to write Cucumber specs (for example) of sufficient clarity that allows an LLM agent team to generate code in any number of code languages that delivers the same outcome, and do that repeatedly?

Then we're at the point where we know the specs work. And is getting to the point where we know the specs work less effort than just coding directly?

We live in exciting times.

Re: Writing code is cheap now

#475

Post by neilwilson »

manuelabeledo wrote: post #322
neilwilson wrote: post #318

Earlier quoted context omitted.

Once writing code is cheap you don't maintain code. You regenerate it from scratch. What you maintain is the specification harness, and change that to change the code. We have to start thinking at a higher level, and see code generation in the same way we currently see compilation.

Unless the specification is also free of bugs and side effects, there is no guarantee that a rewrite would have fewer bugs. Plenty of rewrites out there prove that point.

Yes, but that's the point.

We're not writing code in a computer language any more, we're writing specs in structured English of sufficient clarity that they can be generated from.

The debugging would be on the specs.

Re: Writing code is cheap now

#476

Post by fud101 »

simonw wrote: post #428
trgn wrote: post #427

Earlier quoted context omitted.

haha! do you know details, what domains?

Mark Cuban sold broadcast.com to Yahoo for $5.7bn It was a bit more than a domain name - they had 330 employees and $13.5 million in revenue for a quarter - but that acquisition was definitely peak dot-com boom.

paul graham sold a bunch of buggy lisp macros to yahoo too for a few billion. Wild times.

Re: Writing code is cheap now

#477

Post by hansmayer »

simonw wrote: post #457
hansmayer wrote: post #451

Earlier quoted context omitted.

> Falcons certainly aren't deterministic. Well falcons are not deterministic and are trained to do something in the art of falconry, yes. Still I fail to see an analogy here as it is the falcon gets trained to execute a few specific tasks triggered by specific commands. Much like a dog. The human more or less needs to remember those few commands. We don't teach dogs and falcons to do everything do we ? Although we do…

I've found that using LLMs has had a very material effect on my productivity as a software developer. I write about them to help other people understand how I'm getting such great results and that this is a learnable skill that they can pick up. I know about the METR paper that says people over-estimate the productivity gains. Taking that into account, I am still 100% certain that the productivity gains I'm seeing ar…

That's beside my point. You are trading off the LoC for quality of code. You're not onto some big secret here - I've also built complete fullstack web applications with LLMs, complete with ORM data models and payment integrations. With the issue being....the LLMs will often produce the laziest code possible, such as putting the stripe secret directly into the frontend for anyone with two neurons in their brain to see.... or mixing up TS and JS code...or suggesting an outdated library version.... or for the thousandth time not using the auth functions in the backend we already implemented, and instead adding again session authentication in the expressjs handlers...etc etc. etc. We all know how to "knock out" major applications with them. Again you are not sitting on a big secret that the rest of us have yet to find out. "Knocking out" an application with an LLM most of us have done several times over the last few years, most of them not being toy examples like yours. The issue is the quality of the code and the question whether the effort we have to put into controlling the slot machine is worth the effort.

Re: Writing code is cheap now

#479

Post by AlexeyBelov »

thefaux wrote: post #412
ericol wrote: post #404

Earlier quoted context omitted.

He definitely was paying attention. He had to pause for a second there, arrested by the realization, and was one of the reasons I got an "Exceeds expectations" in one of my KRAs.

It is interesting though that he evidently didn't notice this 2.5X productivity increase until you pointed it out to him.

Surely the manager will now raise his salary by a huge amount! Maybe even 2.5x

Re: Writing code is cheap now

#480

Post by AlexeyBelov »

simonw wrote: post #74
fmbb wrote: post #39

Earlier quoted context omitted.

I don’t think we can expect all workers at all companies to just adopt a new way of working. That’s not how competition works. If agentic AI is a good idea and if it increases productivity we should expect to see some startup blowing everyone out of the water. I think we should be seeing it now if it makes you say ten times more productive. A lot of startups have had a year of agentic AI now to help them beat their c…

OpenClaw went from first commit in late November to Super Bowl commercial (it's meant to be the tech behind that AI.com vaporware thing) in February. (Whether you think OpenClaw is good software is kind of beside the point.)

Right, but what about real companies that solve real people's problems? I think LLMs make a difference for sure, but I haven't yet seen a company that blew past its competitors because of how great their AI usage was. A really great example would be an underdog smallish company that did so in a non-AI field.
Post reply on HN