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

What will LLM-powered software look like in the medium-term future?

vishnumenon.com

Post reply on HN
Print view View original

171–180 of 219 posts

Re: What will LLM-powered software look like in the medium-term future?

#171

Post by shanusmagnus »

sanderjd wrote: post #164
shanusmagnus wrote: post #119

Earlier quoted context omitted.

I think both you and the GP are onto something important. I am one of the vaunted Gen-Xers (this is the first time someone has said anything nice about us, so thanks) and there is something to the idea that my understanding of systems goes down to assembly language (fully) and even CPU architecture (very sketchily) all the way up to, like, web frameworks. So for the stuff I'm usually doing, I understand several layer…

FWIW I'm a (geriatric) millennial, and we were totally taught all that same stuff. And yeah, it totally feels important to me to have this mental model up and down the layers. But I also do wonder whether we're just wrong about that, merely falling prey to nostalgia. My messy answer is that for many projects it's either neutral or an actual hindrance - I have to remind myself to pragmatically not care about stuff tha…

Always important to be on guard for things amenable to self-congratulation. At least, I sure need to be on guard against it :)

Re: What will LLM-powered software look like in the medium-term future?

#172

Post by tines »

famouswaffles wrote: post #170
tines wrote: post #168

Earlier quoted context omitted.

Do you think that this will all function as one giant homogenizing force at the societal level? The AIs will all be trained on the same data, and so will have the same opinions, beliefs, persuasions, etc. It seems like everyone having AIs which are mostly the same will maximize exploitation, and minimize exploration, of ideas.

There are a million different beliefs, opinions etc in the corpus LLMs get trained on and they can predict all of it. It doesn't have to have the same opinions.

Sure, but the probabilities of those beliefs won't be the same as each other, and they will be the same between all users, so that doesn't address my point.

Re: What will LLM-powered software look like in the medium-term future?

#173

Post by gumballindie »

kyleyeats wrote: post #156
gumballindie wrote: post #132

Earlier quoted context omitted.

> they're all the same personality Yeah usually it was the shittiest managers I ever met that shared this belief. It sounds like they all repeat the same thing - gpt is a better google.

Are you calling me a shitty manager? Would you say this to my face? What's wrong with you?

I am not, but there's a tendency among those types that categorise people into narrow sets that they can understand. Also your statement doesn't much make sense. Being a good developer means you understand a wide range of issues, not just spelling in a language and adding if statements. The combination of personalities vary wildly. To be fair, LLMs if anything, will help developers become better managers, simply because developers understand what needs to be done. Instead of decyphering what someone meant by requesting a vague feature, you can ask a statistical system - an ai as some call it - what the average joe wants. And then get it done.

Re: What will LLM-powered software look like in the medium-term future?

#174

Post by klibertp »

amelius wrote: post #106

Take over simple system administration tasks such as (of course giving it full shell access): - install this nVidia driver and make it work with pytorch - get this ethernet connection to $IP working - schedule a daily cron job to make an incremental backup of this harddrive, don't store duplicate files

You've got nerves of steel. It can, and will, hallucinate sudo rm -fr / as a step necessary for configuration at some point (it's even easy to justify by, say, missing the mention of this having to be in a chroot or a container). Russian roulette with your data and setup on the line. Not sure I'm willing to try...

Re: What will LLM-powered software look like in the medium-term future?

#175

Post by vishnumenon »

ryanjshaw wrote: post #38

> I don’t believe that natural language is an adequate medium for conveying instructions with the precision required for many applications. Not clear to me if the author actually uses LLMs to do meaningful work, or is speculating about how they might be used. I've written about 2500 lines of F# for the first time in the past 1.5 weeks using ChatGPT-4 to guide me. It has been an constant back and forth, iterative proc…

I'm the author, and I don't disagree with this at all - I do use LLMs pretty meaningfully in my day-to-day engineering work, and I definitely agree that they hold a ton of promise in situations like the one you mentioned. To be clear, I'm very much bullish on the applications of LLMs to e.g. coding! The point I was trying to make there was just that for _certain_ tasks, the process of chatting with an LLM is, by nature, less precise and more arduous than a purpose-built UX. By analogy, we might have "describe-your-change" functionality in Photoshop, but its no replacement for all the other pixel-perfect editing functionality that it provides, and I'd struggle to imagine a world where Photoshop is ever _replaced entirely_ by a chat UX

Re: What will LLM-powered software look like in the medium-term future?

#176

Post by vishnumenon »

greenie_beans wrote: post #141
reaperman wrote: post #3

A lot of this seems like a nerd’s fantasy. I share these fantasies / desires, but I don’t think its a sober, realistic take on what’s most likely. > Even if an LLM could provide me with a recipe that perfectly suits what I’m looking for, I wouldn’t want to give up the experience of using a recipe search engine and browsing through a large collection of recipes. Me too, but allrecipes.com has already switched from “se…

> Me too, but allrecipes.com has already switched from “search for what you want” to “we’ll tell you what you want”. has anybody ever heard of a cookbook? it's the perfect ux for this. especially if you have a lot of different ones. even better if you collection is mostly physical copies.

OP here, as someone who does love cooking, I've gone down this route pretty heavily in the last few years - been growing my collection of physical cookbooks and definitely enjoy flipping through them in search of inspiration. So, yeah, very much endorse the cookbook UX!

Re: What will LLM-powered software look like in the medium-term future?

#177

Post by gumballindie »

kelseyfrog wrote: post #144
gumballindie wrote: post #50

Earlier quoted context omitted.

To this day i am still wondering what kind of code people write that chatgpt can possibly help with. All my attempts lead to garbage and i would spend more time fixing the output of the chat bot than writing the actual code. It does help with some documentation. But even that has glitches.

Programmers[1] have a complexity bias that interferes with the idea that LLMs can write useful code. I had a problem last week where I wanted to extract sheet names and selection ranges from the Numbers app for a few dozen spreadsheets. ChatGPT, came up with the idea of using Apple script and with a but of coaxing wrote a script to do it. I don't know ApplesScript and I really don't want to learn it. I want to solve…

I am confused - the "code" you described is likely a google search away. Well I mean google has become useless but when it worked it was able to find such stuff in one search. So really all I am getting is that gpt is a better google.

Re: What will LLM-powered software look like in the medium-term future?

#178

Post by vishnumenon »

reaperman wrote: post #3

A lot of this seems like a nerd’s fantasy. I share these fantasies / desires, but I don’t think its a sober, realistic take on what’s most likely. > Even if an LLM could provide me with a recipe that perfectly suits what I’m looking for, I wouldn’t want to give up the experience of using a recipe search engine and browsing through a large collection of recipes. Me too, but allrecipes.com has already switched from “se…

Author of the piece, and I... can't really argue with any of this, tbh. I'll admit both those parts you called out were probably heavily tinged by my own desires, and your more-sober predictions are a very reasonable counterargument for what will happen in the general case. I suppose, especially regarding swappable LLMs, I _do_ only expect it to be an option for devs or sophisticated users; I assume that most folks probably wouldn't care, I'm just hoping there's enough of us that do care that at least some options offer that swappable functionality. Fwiw, I also use Linux (Fedora) as my daily-driver, and I'd be more than content if the predictions from this post came true in a similar vein, e.g. as an OSS option (or family of OSS options) that some subset of users can opt to use.

Re: What will LLM-powered software look like in the medium-term future?

#179

Post by famouswaffles »

tines wrote: post #172
famouswaffles wrote: post #170

Earlier quoted context omitted.

There are a million different beliefs, opinions etc in the corpus LLMs get trained on and they can predict all of it. It doesn't have to have the same opinions.

Sure, but the probabilities of those beliefs won't be the same as each other, and they will be the same between all users, so that doesn't address my point.

again that's up to who's training the models and/or the user. Bing is GPT-4, same exact pre-training but it sounds nothing like chatGPT-4.

LLM probabilities are dynamic. They change based on context. If you want it to behave in a certain way then you provide the context to engineer that.

a particular belief system being most present in training doesn't mean an LLM will always shift probabilities to that system. Such prediction strategies would be awful to fulfil its training objective. Getting it to shift to even the most niche belief is as simple as providing the context to do so.

Re: What will LLM-powered software look like in the medium-term future?

#180

Post by tines »

famouswaffles wrote: post #179
tines wrote: post #172

Earlier quoted context omitted.

Sure, but the probabilities of those beliefs won't be the same as each other, and they will be the same between all users, so that doesn't address my point.

again that's up to who's training the models and/or the user. Bing is GPT-4, same exact pre-training but it sounds nothing like chatGPT-4. LLM probabilities are dynamic. They change based on context. If you want it to behave in a certain way then you provide the context to engineer that. a particular belief system being most present in training doesn't mean an LLM will always shift probabilities to that system. Such…

> again that's up to who's training the models and/or the user.

True, but training is expensive, I imagine that only a few actors will train the popular LLMs, exactly as we are seeing today.

> LLM probabilities are dynamic. They change based on context. If you want it to behave in a certain way then you provide the context to engineer that. ... Getting it to shift to even the most niche belief is as simple as providing the context to do so.

I thought so too, until I tried to get it to agree that 1 + 1 = 3. It would not do that, no matter how much context I provided, likely because the probabilities in the underlying data were so skewed.

Post reply on HN