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

The hidden cost of AI coding

terriblesoftware.org

Post reply on HN
Print view View original

161–170 of 475 posts

Re: The hidden cost of AI coding

#161

Post by selfhoster11 »

dxroshan wrote: post #141
Spivak wrote: post #128

Earlier quoted context omitted.

Even when it hallucinates it still solves most of the unknown unknowns which is good for getting you unblocked. It's probably close enough to get some terms to search for.

I don't think so.How can you be so sure it solves the 'unknown unknowns'?

Sample size of 1, but it definitely did in my case. I've gained a lot more confidence when coding in domains or software stacks I've never touched before, because I know I can trust an LLM to explain things like the basic project structure, unfamiliar parts of the ecosystem, bounce ideas off off, produce a barebones one-file prototype that I rewrite to my liking. A whole lot of tasks that simply wouldn't justify the time expenditure and would make it effort-prohibitive to even try to automate or build a thing.

Re: The hidden cost of AI coding

#162

Post by pdimitar »

elicksaur wrote: post #142
pdimitar wrote: post #17

I don't know man, maybe prompt most of your work, eyeball it and verify it rigorously (which if you cannot do, you should absolutely never touch an LLM!), run a script to commit and push after 3 hours and then... work on whatever code makes you happy without using an LLM? Let's stop pretending or denying it: most of us would delegate our work code to somebody else or something else if we could. Still, prompting LLMs…

>most of us would delegate our work code to somebody else or something else if we could. Laughably narrow-minded projection of your own perspective on others.

[flagged]

Re: The hidden cost of AI coding

#163

Post by aprxi »

ang_cire wrote: post #133

This comment section really shows the stark divide between people who love coding and thus hate AI, and people who hate coding and thus love AI. Honestly, I suspect the people who would prefer to have someone or something else do their coding, are probably the devs who are already outputting the worst code right now.

Cant one enjoy both? After all, coding with AI in practice is still coding, just with a far higher intensity.

Re: The hidden cost of AI coding

#164

Post by pdimitar »

FuckButtons wrote: post #100
pdimitar wrote: post #17

I don't know man, maybe prompt most of your work, eyeball it and verify it rigorously (which if you cannot do, you should absolutely never touch an LLM!), run a script to commit and push after 3 hours and then... work on whatever code makes you happy without using an LLM? Let's stop pretending or denying it: most of us would delegate our work code to somebody else or something else if we could. Still, prompting LLMs…

> Let's stop pretending or denying it: most of us would delegate our work code to somebody else or something else if we could. Hard disagree, I get to hyperfocus on making magical things that surprise and delight me every day.

[flagged]

Re: The hidden cost of AI coding

#165

Post by pjmlp »

frollogaston wrote: post #22
tptacek wrote: post #4

After all, if we lose the joy in our craft, what exactly are we optimizing for? Solving problems for real people. Isn't the answer here kind of obvious? Our field has a whole ethos of open-source side projects people do for love and enjoyment. In the same way that you might spend your weekends in a basement woodworking shop without furnishing your entire house by hand, I think the craft of programming will be just fi…

Same as when higher-level languages replaced assembly for a lot of use cases. And btw, at least in places I've worked, better traditional tooling would replace a lot more headcount than AI would.

I already see this happening with low code, SaaS and MACH architectures.

What used to be a project doing a CMS backend, now is spent doing configurations on a SaaS product, and if we are lucky, a few containers/serveless for integrations.

There are already AI based products that can automate those integrations if given enough data samples.

Many believe AI will keep using current programming languages as translation step, just like those Assembly developers thought compiling via Assembly text generation and feeding into an Assembly would still be around.

Re: The hidden cost of AI coding

#166

Post by selfhoster11 »

dxroshan wrote: post #117
melvinroest wrote: post #113

Earlier quoted context omitted.

> The rest is boiler plate, cargo-culted, Dockerfile, build system and bash environment variable passing circle of hell that I really could care less about. Even more so, I remember making a Chrome extension and feeling intimidated. I knew that I'd be comfortable with most of it given that JS is used but I just didn't know how to start. With an LLM it is way faster to spin up some default config and get going versus…

> What I've noticed in that respect is that I just read what it does and then immediately reason why it's there .... How if it hallucinate and gives you wrong code and explanation? It is better to read documentations and tutorials first.

Do you mean the laconic and incomplete documentation? And the tutorials that range from "here's how you do a hello world" to "draw the rest of the fucking owl" [0], with nothing in between to actually show you how to organise a code base or file structure for a mid-level project?

Hallucinations are a thing. With a competent human on the other end of the screen, they are not such an issue. And the benefits you can reap from having LLMs as a sometimes-mistaken advisory tool in your personal toolbox are immense.

[0]: https://knowyourmeme.com/memes/how-to-draw-an-owl

Re: The hidden cost of AI coding

#167

Post by bgwalter »

RedNifre wrote: post #159
ang_cire wrote: post #133

This comment section really shows the stark divide between people who love coding and thus hate AI, and people who hate coding and thus love AI. Honestly, I suspect the people who would prefer to have someone or something else do their coding, are probably the devs who are already outputting the worst code right now.

Right, just how back in the day, people who loved writing assembly hated high level languages and people who found assembly too tedious loved compilers.

First of all, Lisp, Fortran and COBOL had been around most of the time when assembly was popular. Assembly was used because of resource constraints.

Secondly, you are not writing anything you get from an LLM. You prompt it and it spits out other people's code, stripped of attribution.

This is what children do: Ask someone to fix something for you without understanding the result.

Re: The hidden cost of AI coding

#168

Post by handzhiev »

voidUpdate wrote: post #152
iamleppert wrote: post #3

There's nothing stopping you from coding if you enjoy it. It's not like they have taken away your keyboard. I have found that AI frees me up to focus on the parts of coding I'm actually interested in, which is maybe 5-10% of the project. The rest is boiler plate, cargo-culted, Dockerfile, build system and bash environment variable passing circle of hell that I really could care less about. I care about certain things…

> The rest is boiler plate, cargo-culted, Dockerfile, build system and bash environment variable passing I keep seeing people saying to use an LLM to write boilerplate, but like... do you not just copy that from another project where you already wrote it?

No, because it's usually a few years old and already obsolete - the frameworks and the language have gone through a gazillion changes and what you did in 2021 suddenly no longer works at all.

Re: The hidden cost of AI coding

#169

Post by moooo99 »

handzhiev wrote: post #168
voidUpdate wrote: post #152

Earlier quoted context omitted.

> The rest is boiler plate, cargo-culted, Dockerfile, build system and bash environment variable passing I keep seeing people saying to use an LLM to write boilerplate, but like... do you not just copy that from another project where you already wrote it?

No, because it's usually a few years old and already obsolete - the frameworks and the language have gone through a gazillion changes and what you did in 2021 suddenly no longer works at all.

I mean, the training data also has a cutoff date and changed beyond that are not reflected in the code suggestions.

Also, I know that people love to joke on modern software and JS in particular. But if you take react code from 2020 and drop it into a new react codebase it still works. Even class based components work. Yes, if you jumped on the newest framework bandwagon every time stuff will break all the time, but AI won’t be able to help you with that either. If you went for relatively stable frameworks, you can re use boilerplate completely or with relatively minimal adjustments

Re: The hidden cost of AI coding

#170

Post by selfhoster11 »

docmechanic wrote: post #12
2snakes wrote: post #6

Earlier quoted context omitted.

I read one characterization which is that LLMs don't give new information (except to the user learning) but they reorganize old information.

That’s only true if you tokenize words rather than characters. Character tokenization generates new content outside the training vocabulary.

All major tokenisers have explicit support for encoding arbitrary byte sequences. There's usually a consecutive range of tokens reserved for 0x00 to 0xFF, and you can encode any novel UTF-8 words or structures with it. Including emoji and characters that weren't a part of the model's initial training, if you show it some examples.
Post reply on HN