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

Some thoughts on LLMs and software development

martinfowler.com

Post reply on HN
Print view View original

251–260 of 422 posts

Re: Some thoughts on LLMs and software development

#251

Post by r_lee »

bongodongobob wrote: post #195
achierius wrote: post #161

Earlier quoted context omitted.

I used to be one of those people, then I started saving these scripts in a folder and realized just how much time it saved me. Especially for nontrivial scripts which require a lot of typing or input specification.

This was me before LLMs. Had tons of scripts saved. I just don't see the point anymore "Take this list of users, remove from x group and reset their passwords" takes less time than trying to remember what I named that file and where it's saved. Anything that can be done in under 100 lines isn't worth saving anymore.

Honestly, one of the biggest gains for me with LLMs has been bash scripting. its so great.

especially if you have some saved in the same project and then you just tell it "look at the scripts in x and use that style"

Re: Some thoughts on LLMs and software development

#252

Post by throwboy2047 »

johnnienaked wrote: post #246
computerex wrote: post #241

Earlier quoted context omitted.

The company I work for uses LLM's for digital marketing, the company has over 100M ARR selling products build on top of LLM's with real life measurable impact as measured by KPIs.

Digital marketing is old. What about LLMs gives an advantage to digital marketing?

It’s just plain mean to make the Emperor speak of the thread count of his “clothes”.

Re: Some thoughts on LLMs and software development

#253

Post by whstl »

jeppester wrote: post #107

In my company I feel that we getting totally overrun with code that's 90% good, 10% broken and almost exactly what was needed. We are producing more code, but quality is definitely taking a hit now that no-one is able to keep up. So instead of slowly inching towards the result we are getting 90% there in no time, and then spending lots and lots of time on getting to know the code and fixing and fine-tuning everything…

LLMs are amazing at producing boilerplate, which removes the incentive to get rid of it.

Boilerplate sucks to review. You just see a big mass of code and can't fully make sense of it when reviewing. Also, Github sucks for reviewing PRs with too many lines.

So junior/mid devs are just churning boilerplate-rich code and don't really learn.

The only outcome here is code quality is gonna go down very very fast.

Re: Some thoughts on LLMs and software development

#254

Post by tugberkk »

oo0shiny wrote: post #122

> My former colleague Rebecca Parsons, has been saying for a long time that hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful. What a great way of framing it. I've been trying to explain this to people, but this is a succinct version of what I was stumbling to convey.

Yes, can't remember who said it but LLM's always hallucinate, it is just that they are 90 something percent right.

Re: Some thoughts on LLMs and software development

#255

Post by OtomotO »

tugberkk wrote: post #254
oo0shiny wrote: post #122

> My former colleague Rebecca Parsons, has been saying for a long time that hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful. What a great way of framing it. I've been trying to explain this to people, but this is a succinct version of what I was stumbling to convey.

Yes, can't remember who said it but LLM's always hallucinate, it is just that they are 90 something percent right.

Which totally depends on your domain and subdomain.

E.g. Programming in JS or Python: good enough

Programming in Rust: I can scrap over 50% of the code because it will

a) not compile at all (I see this while the "AI" types)

b) not meet the requirements at all

Re: Some thoughts on LLMs and software development

#256

Post by aitchnyu »

oo0shiny wrote: post #122

> My former colleague Rebecca Parsons, has been saying for a long time that hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful. What a great way of framing it. I've been trying to explain this to people, but this is a succinct version of what I was stumbling to convey.

All models are wrong, some are merely useful - 1976/1933/earlier adage.

Re: Some thoughts on LLMs and software development

#257

Post by wk_end »

Cthulhu_ wrote: post #249
FromTheFirstIn wrote: post #172

Earlier quoted context omitted.

It’s funny how nothing seems to be AI’s fault.

That's because it's software / an application. I don't blame my editor for broken code either. You can't put blame on software itself, it just does what it's programmed to do. But also, blameless culture is IMO important in software development. If a bug ends up in production, whose fault is it? The developer that wrote the code? The LLM that generated it? The reviewer that approved it? The product owner that decided…

Blameless culture is important for a lot of reasons, but many of them are human. LLMs are just tools. If one of the issues identified in a post-mortem is "using this particular tool is causing us problems", there's not a blameless culture out there that would say "We can't blame the tool..."; the action item is "Figure out how to improve/replace/remove the tool so it no longer contributes to problems."

Re: Some thoughts on LLMs and software development

#258

Post by johnnienaked »

computerex wrote: post #238
johnnienaked wrote: post #221

Earlier quoted context omitted.

Technology does not always help people, in fact often it creates new problems that didn't exist before. Also telling someone to "adapt to the times" is a bit silly. If it helped as much as its claimed, there wouldn't be any need to try and convince people they should be using it. A LOT of parallels with crypto, which is still trying to find its killer app 16 years later.

"It is difficult to get a man to understand something when his salary depends upon his not understanding it"

It's also difficult to get a man to understand something if you stubbornly refuse to explain it.

Instead of this crypto-esque hand waving, maybe you can answer me now?

Re: Some thoughts on LLMs and software development

#259

Post by pjmorris »

aitchnyu wrote: post #256
oo0shiny wrote: post #122

> My former colleague Rebecca Parsons, has been saying for a long time that hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful. What a great way of framing it. I've been trying to explain this to people, but this is a succinct version of what I was stumbling to convey.

All models are wrong, some are merely useful - 1976/1933/earlier adage.

Generally attributed to George Box

Re: Some thoughts on LLMs and software development

#260

Post by johnnienaked »

raducu wrote: post #228
johnnienaked wrote: post #222

Earlier quoted context omitted.

No one seems to be able to grasp the possibility that AI is a failure

> No one seems to be able to grasp the possibility that AI is a failure. Do you think by the time GPT-9 comes, we'll say "That's it, AI is a failure, we'll just stop using it!" Or do you speak in metaphorical/bigger picture/"butlerian jihad" terms?

I don't see the use-case now, maybe there will be one by GPT-9
Post reply on HN