Live data from Hacker News

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

vishnumenon.com

51–60 of 219 posts

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

#51

> 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 feel like such a jerk for not wanting to use chatgpt for all that. It's not just mild paranoia about feeding it input I prefer be kept private but I just don't enjoy having someone else do half the thinking for me I guess.

I mean, I don't like intellisense either (but simple autocomplete is fine). Perhaps it is because I only code to help with my job, I don't get paid to have a lot of good quality code output.

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

#52

@vishnumenon, thanks for writing this up. I might do a followup blog on this, for now here is a comment :) This article is close to my heart as I've been working on craftcraft.org with similar perspective. 1. Chat UX Consolidation: I agree that having crappy chat UIs everywhere is very suboptimal. Perhaps having a complete UX as a component is another solution here. We took many months to get http://chatcraft.org fro…

Really good stuff, but some minor things: your url doesn't work; went to your twitter profile, and it seems you meant https://chatcraft.org ? Also, you are un-dm-able on twitter. (I am @eating_entropy if you want to talk more)

that's the right link :)

would be great to chat on discord https://discord.gg/JsVe9ZuZCn

(updated discord link)

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

#53

> 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…

Bit of an aside, but I wonder if the rise of LLMs will lead to new programming languages being much slower to be adopted. Like you said, you might have given up on F# without ChatGPT assistance, and the main way ChatGPT is able to help with F# is because of all of the example code it's been trained on. If developers rely more and more on LLM aid, then a new language without strong LLM support might be a dealbreaker t…

I've also wondered this - including if we might see a breed of 'higher level' languages (i.e. much higher level than Python) which can then be 'AI compiled' into highly efficient low level code.

i.e. the advantages of an even-higher-level python that's almost like pseudo-code with assembly-level speed and rust-level safety, where some complexity can be abstracted out to the LLM.

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

#54

> 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.

I've used it on this side project for:

- A rough crash course in F#. I'll say "what's the equivalent in F# of this C# concept?". It will often explain that there is no direct concept, and give me a number of alternative approaches to use. I'll explain why I'm asking, and it'll walk through the pros/cons of each option.

- Translating about 800 lines of TypeScript JSON schema structures to F#. A 1:1 translation is not possible since TypeScript has some features F# doesn't, so ChatGPT also helped me understand the different options available to me for handling that.

- Translating psuedo-code/algorithms into idiomatic F# as a complete F# beginner. The algorithms involve regex + AST-based code analysis and pattern matching. This is a very iterative process, and usually I ask for one step at a time and make sure that step works before I move onto the next.

- Planning design at a high-level and confirming whether I've thought through all the options carefully enough.

- Adding small features or modifications to working code: I present part of the function plus relevant type definitions, and ask it for a particular change. This is especially useful when I'm tired - even though I could probably figure it out myself, it's easier to ask the bot.

- Understanding F# compiler errors, which are particularly verbose and confusing when you're new to the language. I present the relevant section of code and the compiler error and 90% of the time it tells me exactly what the problem and solution is; 5% of the time we figure it out iteratively. The last 5% tends I have to stumble through myself.

- Confirming whether my F# code is idiomatic and conforming to F# style.

- Yes it makes mistakes. Just like humans. You need to go back and forth a bit. You need to know what you're doing and what you want to achieve; it's a tool, not magic.

Note: this is the commercial product, ChatGPT-4. If you're using the free ChatGPT 3.5, you will not be anywhere near as productive.

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

#55
post #51

> 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 feel like such a jerk for not wanting to use chatgpt for all that. It's not just mild paranoia about feeding it input I prefer be kept private but I just don't enjoy having someone else do half the thinking for me I guess. I mean, I don't like intellisense either (but simple autocomplete is fine). Perhaps it is because I only code to help with my job, I don't get paid to have a lot of good quality code output.

Don't beat yourself up. As a mathematically-oriented software engineer I also have little to no interest in using LLMs to help with coding. It feels like the people that do are the builders, i.e. interested in quickly knocking up something that works most of the time. Which is great from a business perspective. I can't help but see my programming output as an artistic expression of my thought, and therefore find it difficult to give up the hands-on construction to others (be it LLMs or juniors).

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

#57
post #40

My prediction: knowledge will start to be reformatted into an LLM directly and knowledge providers will stop publishing it otherwise. Thus the chat interface will both improve and protect knowledge access once the traditional formats are not published anymore. This will come together with the downfall of search, a prime driver why so much knowledge was published on the web. Search will start to drown in an explosion…

Models still need to search. Tuning and reference augmented generation go hand in hand.

Indeed, but search exist for humans. And if search becomes unusable because the web gets filled with AI noise, humans will stop using search.

And also for models, to feed them with data generated by AI seems like an issue to me.

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

#58
post #51

> 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 feel like such a jerk for not wanting to use chatgpt for all that. It's not just mild paranoia about feeding it input I prefer be kept private but I just don't enjoy having someone else do half the thinking for me I guess. I mean, I don't like intellisense either (but simple autocomplete is fine). Perhaps it is because I only code to help with my job, I don't get paid to have a lot of good quality code output.

I know exactly why I don't want to use ChatGPT.

I love to write code, I love to modify existing code too.

I do not love to read and then fix code after someone all the time. With ChatGPT I have to read then understand then fix code after ChatGPT every time.

Also, I do not love to fix code that often contains hallucination.

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

#59

> 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.

I used chatgpt4 to generate python code which generates c++ code for a hobby project of mine using a library I've never used before. The iteration speed is ridiculously good and no one in any of the IRC or discord channels I visited pointed me even in the general direction of such a simple solution.

https://chat.openai.com/share/d041af60-b980-4972-ba62-3d41e0... https://github.com/Mk-Chan/gw2combat/blob/master/generate_co...

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

#60

Earlier quoted context omitted.

While I agree some longform articles could use a bulleted summary, I think the act of blog-writing is as much an exercise of the writer coming to terms with the subject as us enjoying the piece. Abridging an idea comes easier after exploring its breadth and width, and I am supportive of anyone who tries it out in the open.

I agree with this and often even find myself leaving drafts around to read, re-read, and edit as I flesh out the ideas and thoughts in my own brain. Writing in long form is its own process of mental synthesis.

People who want AI to write for them don’t understand this process.
Post reply on HN