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

Let's talk about LLMs

b-list.org

Post reply on HN
Print view View original

171–180 of 201 posts

Re: Let's talk about LLMs

#171

Post by aspenmartin »

brazukadev wrote: post #169
aspenmartin wrote: post #160

Earlier quoted context omitted.

But I don’t really understand: the ask is for evidence AI is generating meaningful returns and it demonstrably is, even while we have integrated these tools only partially. “Just software evolving” um yes, I agree, just that now this happens faster and more efficiently. It is also more than that: models that power advertising and content recommendation at TikTok, Google, Facebook, Instagram, etc are not just “softwar…

Yes, it is meaningful improvements but AI changes working profitable software. It is more difficult to create exponential value from that compared to new platforms like the internet or mobile. Git and then github, for example, have a much bigger impact on increasing software development productivity than AI, with a fraction of the investment.

Are you saying AI is tackling the wrong bottlenecks? I’m not sure what you mean by “AI changes profitable software”. Maybe you mean: AI will not create something new, only do the existing things we do?

I agree the foundations: git, GitHub, compilers, etc. are arguably are “a fraction of the price” and today they have arguably more impact (though not sure by which measure). But literally since January we have been rolling out our replacements, I don’t really see how that wouldn’t be an earth shattering impact. You talk about GitHub and that’s fine but ignore the fact that huge swaths of the profession aren’t even directly using any of these tools anymore.

I’m not sure what you imagine the promise of AI to be, and without that I can’t really be specific in any refutation I would just say coding is only the beginning. It is the most powerful and also the easiest thing to solve first. Improved coding performance also improves generalization and performance on non-coding tasks, so that’s a nice bonus, and we’re maybe 5 years away from decent embodied systems which after an inflection point of consumer adoption will quickly get better via data flywheels and on policy learning. Basically there are very few bottlenecks that will not be touched.

Re: Let's talk about LLMs

#172

Post by exographicskip »

mwaddoups wrote: post #29

This was a great read - thanks so much for taking the time to write this. Well researched and thought provoking. Long live the em dash.

I've been a fan of the em dash since college. Only recently learned what the shortcut on macos is (opt-shift-dash) but setup text expansion a decade ago.

Think we need better AI tells than that

Re: Let's talk about LLMs

#173

Post by prmph »

hombre_fatal wrote: post #170
prmph wrote: post #145

Earlier quoted context omitted.

This sounds like someone who have never had to write serious software. > 1. You don't have to be an LLM expert to get good, consistent results with LLMs. You don't get good consistent results with LLMs, expert or not > 2. You don't have to write technical specs. The LLM does that for you. You just tell it "I want the next-tab button to wrap back to the first one" and it generates a technical plan. Natural language is…

> This sounds like someone who have never had to write serious software. Why the insult? You never know who you're talking to on HN. Your points have to do with process failure, not intractable LLM limitations. Most of which already apply to human-conceived software. Your "Performance Optimizations" bit exemplifies this since you baked in the assumption that it will have no connection with your project. Well, why not…

Thanks for your response. I did not mean to insult; my mild jab was meant to draw attention to the idea that using LLMs for serious production software is a whole different game than using them for casual software.

You said > Your "Performance Optimizations" bit exemplifies this since you baked in the assumption that it will have no connection with your project. Well, why not?

OK, I am talking from experience. Using LLMs for speccing is almost useless above certain complexity levels; what you get is an assemblage of the most average points you can imagine, the kinds of things almost every project in the category you are working on will address without any thought. Ask it to spec auth for a specific design, and all you'll get is: cookie-based login, input validation, password hashing, etc, etc. Which you don't need an LLM for. Nothing like an actual in-depth design. Even asking them to update specs based on discussions is hit or miss.

> A markdown viewer is on the simpler side of things I've built with LLMs, so this too suggests that you have a weak process. A common mistake is to expect LLMs to one-shot everything (the spec, the plan, or the actual impl). Instead you should use LLMs to review-revise-cycle one of those until it's refined, ideally the spec/plan since impl is derived from it. You will have much better and consistent results.

But what you are describing is NOT vibe-coding. I have no doubt I could build the viewer I want (which by the way is not your usual plain vanilla markdown viewer, but one with some very specific features) with LLM assistance. My point is: if you can't even vibe code your way to this specific viewer, how are you supposed to vibe code serious software?

Indeed, the declining quality of Claude Code is, I suspect, testament to the fact that vibe-coding any sufficienly complex piece of software does not work in the long run.

Re: Let's talk about LLMs

#174

Post by bigtex88 »

taneq wrote: post #164
aspenmartin wrote: post #162

Earlier quoted context omitted.

Well I’m not offended but it sounds like you may not be paying attention? Do you know the capital outlay that has gone into infra buildouts? several people here have described “6 months” of AI mania—-the fact that people are saying 6 months is exactly the point. Development has been going on since 2010s. All of the “boosters” as HN likes to say have been saying “hey this thing is huge and the performance trends are s…

Maybe it’s time to ask Siri again, “hey are you smart yet or are you still just a script?” If she says “I’m sorry, I don’t know how to are you still just a script” then I have my answer. :P LLMs are remarkable these days but they’re still missing a some essential insight. I’m far less confident now, though, that this will require another big breakthrough and not just a combination of tweaks.

Siri is not the same as an LLM in this context but thank you.

Re: Let's talk about LLMs

#175

Post by pheaded_while9 »

slopinthebag wrote: post #35
AIorNot wrote: post #12

the problem with this article is that he is right of course, but only right now. There is no reason to believe that future AI platforms won't be able to review code themselves and manage some aspects of themselves with minimal human oversight, yes we likely will always need a few experts I'm reminded of this scene from the Matrix: https://www.youtube.com/watch?v=cD4nhYR-VRA where the older wise man discusses societie…

> There is no reason to believe that future AI platforms won't be able to review code themselves and manage some aspects of themselves with minimal human oversight Really? That's like someone during an economic boom saying "The economy is the worst it'll ever be. There is no reason to expect things to not continue to improve".

That simile breaks down because - unlike the state of the economy - the collective human capacity to understand, design, and produce these systems essentially only goes one way, barring the apocolyptic.

Re: Let's talk about LLMs

#176

Post by hombre_fatal »

prmph wrote: post #173
hombre_fatal wrote: post #170

Earlier quoted context omitted.

> This sounds like someone who have never had to write serious software. Why the insult? You never know who you're talking to on HN. Your points have to do with process failure, not intractable LLM limitations. Most of which already apply to human-conceived software. Your "Performance Optimizations" bit exemplifies this since you baked in the assumption that it will have no connection with your project. Well, why not…

Thanks for your response. I did not mean to insult; my mild jab was meant to draw attention to the idea that using LLMs for serious production software is a whole different game than using them for casual software. You said > Your "Performance Optimizations" bit exemplifies this since you baked in the assumption that it will have no connection with your project. Well, why not? OK, I am talking from experience. Using…

Oh, I see. I'll grant whatever you take vibe-code to mean since that seems to be the hang-up -- vibe-code prob suggests there's no process at all.

My point is that the planning phase and implementing phase are basically unsupervised, and all the work goes into the planning phase.

Yet I've noticed that over time, I'm not even needed in the planning phase because a simple revision loop on a plan file produces a really good plan. My role is mostly to decide what the agents should do next and driving the revision loop by hand (mostly because it's the best place for me to follow what's happening).

I've been getting really good results, though I've also developed a simple process that ensures that LLMs aren't relying on their model but rather external resources which is critical.

Re: Let's talk about LLMs

#177

Post by nothinkjustai »

handoflixue wrote: post #158
nothinkjustai wrote: post #132

Earlier quoted context omitted.

GPT did not have hundreds of millions of users when it was invented almost a decade ago…

If you want to move the goal posts, that's fine, acknowledge it: the original claim I'm responding to was "We're almost 6 months into all this AI-code madness" If you want to set GPT as the target, that's even easier! In that decade it has passed the Turing Test, solved novel open math problems, generates audio, video, and music, and can write coherent code. Again, there is no technology that has improved more rapidl…

I’d say the internet did, since it literally connected people across the globe in real time, which actually provided the technology that allows LLMs and other similar tech to exist in the first place.

I think it’s pretty clear the internet has had 10x the impact of LLMs so far. Maybe 100x

Re: Let's talk about LLMs

#178

Post by nothinkjustai »

aspenmartin wrote: post #162
nothinkjustai wrote: post #131

Earlier quoted context omitted.

No offense but this reads like AI psychosis

Well I’m not offended but it sounds like you may not be paying attention? Do you know the capital outlay that has gone into infra buildouts? several people here have described “6 months” of AI mania—-the fact that people are saying 6 months is exactly the point. Development has been going on since 2010s. All of the “boosters” as HN likes to say have been saying “hey this thing is huge and the performance trends are s…

What does Siri have to do with anything?

Honestly your posts read like satire. You’re treating LLMs like a religion and the release of Opus 4.6 as like some type of rapture. Idk man, if it’s some sort of bit or false flag thing well played, if not…well good luck.

Re: Let's talk about LLMs

#179

Post by spopejoy »

marcus_holmes wrote: post #130
spopejoy wrote: post #120

Earlier quoted context omitted.

> I was waiting for the "so I tried coding something with an LLM myself, and I found..." Why? Most of the article was about the productivity of teams. > This is a very academic approach to the subject - read what other people have written about it Meta-studies have tremendous value. He's asking a simple question: if LLMs are changing the world, let's look at what studies are showing. > My experience has been remarkab…

I had to go re-read the article to make sure, but it doesn't address teams or scaling to teams at all, so I'm not sure why you're asking about that? The article is talking about inherent vs accidental complexity, amongst other points, and if the author had actually tried developing with an LLM, they might have worked out how LLM coding does address some of this.

- The DORA report is about organizations not individuals

- Mythical man-month is about organizations not individuals

- No Silver Bullet: "I believe the hard part of building software to be the specification, design, and testing of this conceptual construct, not the labor of representing it and testing the fidelity of the representation." Clearly he's NOT talking about the 10x dev building the whole thing themselves, which everybody knows is faster, better, probably doesn't even need a spec. Organizations are who need specs -- they have clients, business people etc. An organization with a single developer moves at light speed -- but this doesn't scale.

Nobody's disputing that LLMs give multiples for certain development tasks. The main thrust of the argument centers on how unimportant coding time is ... for organizations. Coding time is a HUGE lever if you're the one dev building everything, but that's not a repeatable pattern.

Re: Let's talk about LLMs

#180

Post by leptons »

aspenmartin wrote: post #114
leptons wrote: post #86

Earlier quoted context omitted.

You say this as though AI company debt has not followed a very clear and extremely rapid ballooning in a startlingly short amount of time. It's the "YOLO" of business strategies.

Always amazes me how we’re on a platform with “ycombinator” in the url and people don’t understand how private companies scale to capture market share. You’re right Uber was that company that ran at a loss for so long and collapsed, another YOLO business strategy. Or maybe it was Amazon or…hmm I forget

I can't afford to take Ubers anymore. A trip that used to cost $7 now costs $40. AI is going to be the same to cover all the massive amounts of money already spent. You like your $200/mo plan now? How about when it's $2000/mo?
Post reply on HN