Some thoughts on LLMs and software development • Hacker News Board

Re: Some thoughts on LLMs and software development

#391

Post by sarchertech » Sat, Aug 30, 2025, 12:41 AM UTC

jama211 wrote: post #375

sarchertech wrote: post #318

Earlier quoted context omitted.

I use AI for most of those things. And I think it probably saves me a bit of time. But in that study that came out a few weeks ago where they actually looked at time saved, every single developer overestimated their time saved. To the point where even the ones who lost time thought they saved time. LLMs are very good at making you feel like you’re saving time even when you aren’t. That doesn’t mean they can’t be a ne…

I mean, I used to average 2 hours of intense work a day and now it’s 1 hour.

How are you tracking that? Are you keeping a log, or are you just guessing? Do you have a mostly objective definition of intense work or are you just basing it on how you feel? Is your situation at work otherwise exactly the same, or have you gotten into a better groove with your manager? Are you working on exactly the same thing? Have you leveled up with some more experience? Have you learned the domain better?

Is your work objectively the same quality? Is it possible that you are producing less but it’s still far above the minimum so no one has noticed? Is your work good enough for now, but a year from now when someone tries to change it, it will be a lot harder for them?

Based on the only real studies we have, humans grossly overestimate AI time savings. It’s highly likely you are too.

Re: Some thoughts on LLMs and software development

#392

Post by jychang » Sat, Aug 30, 2025, 3:12 AM UTC

_heimdall wrote: post #390

jychang wrote: post #385

Earlier quoted context omitted.

Do you also disagree with the use of the name “tree” in a computer science class? Again, nobody thinks trees in computer science contains squirrels, nobody thinks airplanes are birds, and nobody thinks a neuron in a ML model contains axons and dendrites. This is a weird hill to die on. Are you gonna complain that the word “photograph” is “light writing” but in reality nobody is writing anything so therefore the word…

I would disagree with anyone that wants to say they are the same as a natural tree, sure. I don't believe the term photograph was repurposed when cameras were invented, that example doesn't fit. More importantly, I argued that neuron has a very specific biological meaning and its a misuse to use the term for what is ultimately running on silicon. Your claim was that they are neurons, period. You didn't expand on that…

https://en.m.wikipedia.org/wiki/Artificial_neuron

Re: Some thoughts on LLMs and software development

#393

Post by _heimdall » Sat, Aug 30, 2025, 4:18 AM UTC

jychang wrote: post #392

_heimdall wrote: post #390

Earlier quoted context omitted.

I would disagree with anyone that wants to say they are the same as a natural tree, sure. I don't believe the term photograph was repurposed when cameras were invented, that example doesn't fit. More importantly, I argued that neuron has a very specific biological meaning and its a misuse to use the term for what is ultimately running on silicon. Your claim was that they are neurons, period. You didn't expand on that…

https://en.m.wikipedia.org/wiki/Artificial_neuron

What's your point with that link? I'm well aware that people use the term neuron in AI research and acknowledged it a few comments up. I disagree with the use of term, I'm not arguing that the term isn't used.

Re: Some thoughts on LLMs and software development

#394

Post by seunosewa » Sat, Aug 30, 2025, 8:23 AM UTC

scott_w wrote: post #379

seunosewa wrote: post #360

Earlier quoted context omitted.

We do the same thing. We pick words that are statistically likely to get us what we want. And much of it is unconscious. You don't formally reason about every word you speak. You are focused on your objective, and your brain fills in the gaps.

We absolutely do not "pick words that are statistically likely to get us what we want." We use words to try to articulate (to varying levels of success) a message that we want to communicate. The words, tone, speed, pitch, etc. all convey meaning. > And much of it is unconscious. That does not mean we're "picking words statistically likely to get us what we want," it means "our brains do a lot of work subconsciously.…

The LLM objective is whatever they are trained to do, whether it's completing text, obeying instructions, coding, etc.

In pre-training, we drop a lot of human-written text in them. This allows them to learn the rules of language and grammar and common language patterns. At this stage, the objective is to predict the next token that makes sense to human beings.

Examples: The capital of US is ... Why did the chicken ...

The next step is instruct training, where they are trained to follow instructions. At this point, they are predicting the next token that will satisfy the user's instructions. They are rewarded for following instructions.

Next step, they are trained to reason by feeding them with reasoning examples to get them going, and then rewarding them whenever their reasoning leads them to good answers. They learn to predict the next reasoning token that will lead them to the best answers.

The objective is imparted by their training. They are "rewarded" when their output satisfies the objective, so that as they are trained, they get better and better at achieving the objectives of the training.

Re: Some thoughts on LLMs and software development

#395

Post by bluefirebrand » Sat, Aug 30, 2025, 5:22 PM UTC

discreteevent wrote: post #283

bluefirebrand wrote: post #213

Earlier quoted context omitted.

> When I have to deeply understand what an llm created Which should be always in my opinion Are people really pushing code to production that they don't understand?

They are, because in fairness in a lot of cases it just doesn't matter. It's some website to get clicks for ads and as long as you can vibe use it it's good enough to vibe code it.

I wouldn't be caught dead building garbage like that

Re: Some thoughts on LLMs and software development

#396

Post by Kiro » Sat, Aug 30, 2025, 6:07 PM UTC

johnnienaked wrote: post #365

Kiro wrote: post #289

Earlier quoted context omitted.

Absence of your need isn't evidence of no need.

This is true, but I've never heard of a use case. To which you might reply, "doesn't mean there isn't one," which you would be also right about. Maybe you know one.

I presume your definition of use case is something that doesn't include what people normally use it for. And I presume me using it for coding every day is disqualified as well.

Re: Some thoughts on LLMs and software development

#397

Post by jama211 » Sat, Aug 30, 2025, 7:37 PM UTC

sarchertech wrote: post #391

jama211 wrote: post #375

Earlier quoted context omitted.

I mean, I used to average 2 hours of intense work a day and now it’s 1 hour.

How are you tracking that? Are you keeping a log, or are you just guessing? Do you have a mostly objective definition of intense work or are you just basing it on how you feel? Is your situation at work otherwise exactly the same, or have you gotten into a better groove with your manager? Are you working on exactly the same thing? Have you leveled up with some more experience? Have you learned the domain better? Is y…

_sigh_. Really dude? Just because people overestimate them on average doesn’t mean every person does. In fact, you should be well versed enough about the statistics to understand that it will be a spectrum that is highly dependent on both a persons role and how they use it.

For any given new tool, a range of usefulness that depends on many factors will affect people differently as individuals. Just because a carpenter doesn’t save much time because Microsoft excel exists doesn’t mean it’s not a hugely useful tool, and doesn’t mean it doesn’t save a lot of time for accountants, for example.

Instead of trying to tear apart my particular case, why not entertain the possibility that it’s more likely I’m reporting pretty accurately but it’s just I may be higher up that spectrum - with a good combo of having a perfect use case for the tool and also using the tool skilfully?

Re: Some thoughts on LLMs and software development

#398

Post by jama211 » Sat, Aug 30, 2025, 7:41 PM UTC

mexicocitinluez wrote: post #319

jama211 wrote: post #275

Earlier quoted context omitted.

Finally, an opinion on here that’s reasonable and isn’t “AI is perfect” or “AI is useless”.

One of the things that has struck me as odd is just how little self-awareness devs have when talking about "skin in the game" with regard to CEO's hawking AI products. Like, we have just as much to lose as they have to gain. Of course a part of us doesn't want these tools to be as good as some people say they are because it directly affects our future and livelihood. No, they can't do everything. Yes, they can do som…

Indeed. You’d think people with a tech background would be less likely to be so irrationally emotional about these things, but obviously not. Fear and devotion it turns out are both incredibly blinding motivators.

Re: Some thoughts on LLMs and software development

#399

Post by jama211 » Sat, Aug 30, 2025, 7:42 PM UTC

kaosoaksh wrote: post #334

mexicocitinluez wrote: post #319

Earlier quoted context omitted.

One of the things that has struck me as odd is just how little self-awareness devs have when talking about "skin in the game" with regard to CEO's hawking AI products. Like, we have just as much to lose as they have to gain. Of course a part of us doesn't want these tools to be as good as some people say they are because it directly affects our future and livelihood. No, they can't do everything. Yes, they can do som…

> doesn’t want these tools to be as good as some people say they are No, this is because that would mean AGI. And it’s obviously not that.

And they’re similarly not as useless as others say they are, as they draw crosses in the air and hiss at the heathen tech to go away.

Re: Some thoughts on LLMs and software development

#400

Post by jama211 » Sat, Aug 30, 2025, 7:49 PM UTC

globular-toast wrote: post #381

jama211 wrote: post #269

Earlier quoted context omitted.

Only when purely vibe coding. AI currently saves a LOT of time if you get it to generate boilerplate, diagnose bugs, or assist with sandboxed issues. The proof is in the pudding. The work I do takes me half as long as it used to and is just as high in quality, even though I manage and carefully curate the output.

I don't write much boilerplate anyway. I long ago figured out ways to not do that (I use a computer to do repetitive tasks for me). So when people talk about boilerplate I feel like they're only just catching up to me, not surpassing me. As for catching bugs, maybe, but I feel like it's pot luck. Sometimes it can find something, sometimes it's just complete rubbish. Sometimes worth giving it a spin but still not conv…

Like any tool, it has use cases where it excels and use cases where it’s pretty useless.

Unfamiliar code bases is a great example, if it’s able to find the bug it could do so almost instantly, as opposed to a human trying to read through the code base for ages. But for someone who is intimately familiar with a code base, they’ll probably solve the problem way faster, especially if it’s subtle.

Also say if your job is taking image designs and building them in html/css, just feeding it an image getting it to dump you an html/css framework and then you just clean up the details of will save you a lot of time. But on the flip side if you need to make critically safe software where every line matters, you’ll be way faster on your own.

People want to give a black and white “ai is bad” or “ai is great”, but the truth _as always_ is “it depends”. Humans aren’t very good at “it depends”.