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

141–150 of 219 posts

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

#141

Post by greenie_beans »

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.

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

#142

Post by vorpalhex »

alluro2 wrote: post #42

I was hoping for some clever ideas about direction of software / UIs, and new use-cases for LLMs / AI, since for now I'm still struggling and have a lack of vision, it seems. For example, I work on developing a logistics management and route optimization platform. If I try to envision new features that could be unlocked through AI or just LLMs, I basically get nothing back from my feeble brain, that I would fit into…

Problem identification.

Given all the log data for the last N packages, analyze for anomalies and hypothesis as to their cause. Eg is there a specific shipper, warehouse or driver causing problems?

ML does well when you have too much data for a human to wrangle and the search target is well described.

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

#143

Post by Closi »

jprete wrote: post #96
Closi wrote: post #90

Earlier quoted context omitted.

I mean why is f# the goal, and could we write a better f# with the use of AI. As an example, why not write in f# and let an 'AI-compiler' optimise the code... The AI-compiler could then make sure all the code is type safe, add in manual memory management to avoid the pitfalls of garbage collection, add memory safety etc - all the hard bits. And then if we gave the AI-compiler those sort of responsibilities, then we c…

This doesn’t require AI, it requires higher-level languages than we have that can express intent more directly.

In current generation language there is definitely a trade-off between language productivity (i.e. speed of writing) and features such as speed and memory-safety.

So far we haven't been able to close this gap fully with current compilers and interpreters (i.e. python still runs slower than C).

It seems like that gap could be closed through, for example, automated refactoring into a rust-like language during compilation, or directly into more-efficient byte-code/ASM that behaves identically.

And surely if that is a possibility, that would affect language design (e.g. if you can abstract away some complexity around things like memory management).

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

#144

Post by kelseyfrog »

gumballindie wrote: post #50
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…

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 my problem and its 10 lines of AppleScript did just that.

We're nowhere near LLMs being capable of writing codebases, be we are here for LLMs being able to write valuable code because those concepts are orthogonal.

1. some, most

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

#145

Post by reaperman »

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.

Yes but Allrecipes.com didn't cost me hundreds of dollars to get 20-30 high quality cookbooks and had 10,000+ recipes. More importantly, I could trust that the highest-rated recipes, while not necessarily the "best", would be stupid-proof. The only way that recipes got universally high feedback from the average home cook on allrecipes.com is if you could accidentally double or halve any ingredient and it would still taste good. Cookbooks often contain recipes which, while better, are also more particular and require a higher skill floor.

I could also quickly filter against recipes which contained ingredients I didn't like, or filter for recipes which used ingredients I already have on hand.

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

#146

Post by brandall10 »

wbm1 wrote: post #115
croo wrote: post #111

Earlier quoted context omitted.

Exactly! Most will have a name given by its owner, a pet of sort but much more in function. You will need to reach a certain age to get it, the beginning of adulthood. People will mourn them and there will be real world AI cementeries. Diffie Whitfield envisioned an internet highway where every computer is connected to every other in 1974 and then went on to find out how to do that communication in secure channels.[1…

The more personal value it holds, the more risk it has. Imagine gaining access to this digital daimon of someone, it'll be like accessing their most inner thoughts. The upside however could be exponential personal growth. I've seen many examples of real life twins that basically live as a superhuman individual. E.g. the Liberman twins. This tech could be a digital equivalent of that.

Small correction - Daniil and David Liberman are just brothers, not twins.

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

#147

Post by hirundo »

inimino wrote: post #127
hirundo wrote: post #121

Earlier quoted context omitted.

> the next generation will see it as the current see the TV - unimportant old boring low-entropy data which is not entertaining anymore. Don't you mean high-entropy data? High entropy data would be less orderly, more compressible, and have a lower signal to noise ratio ... like TV shows compared to a textbook.

Low entropy data is what's more compressible. High entropy means unpredictable, which could mean high noise (like TV static which is incompressible) or high signal as GP intended.

Thank you. I just learned about Shannon Entropy and that it grows with information content. The negative sign in the formula is due to the negative log of the normalized population probability.

https://math.stackexchange.com/questions/395121/how-entropy-...

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

#148

Post by freckletonj »

In answer to the same question I built UniteAI https://github.com/freckletonj/uniteai

It's local first, and ties many different AIs into one text editor, any arbitrary text editor in fact.

It does speech recognition, which isn't useful for writing code, but is useful for generating natural language LLM prompts and comments.

It does CodeLlama (and any HuggingFace-based language model)

It does ChatGPT

It does Retrieval Augmented Gen, which is where you have a query that searches through eg PDFs, Youtube transcripts, code bases, HTML, local or online files, Arxiv papers, etc. It then surfaces passages relevant to your query, that you can then further use in conjunction with an LLM.

I don't know how mainstream LLM-powered software looks, but for devs, I love this format of tying in the best models as they're released into one central repo where they can all play off each others' strengths.

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

#149

Post by inimino »

hirundo wrote: post #147
inimino wrote: post #127

Earlier quoted context omitted.

Low entropy data is what's more compressible. High entropy means unpredictable, which could mean high noise (like TV static which is incompressible) or high signal as GP intended.

Thank you. I just learned about Shannon Entropy and that it grows with information content. The negative sign in the formula is due to the negative log of the normalized population probability. https://math.stackexchange.com/questions/395121/how-entropy-...

Yes. You can also take the log of the reciprocal probability (or "luck") and then you don't need the negative sign. This value is the expected number of trials you would need for the outcome to occur once. I find this presentation a bit more intuitive. See also Boltzmann entropy S = k log W which takes this form.

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

#150

Post by kristianp »

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…

The llm effect may enable people to use languages that are harder to write, but produce a more maintainable and/or performant product. Maybe it's finally time to learn rust or ocaml!
Post reply on HN