The Leverage of LLMs for Individuals • Hacker News Board

Re: The Leverage of LLMs for Individuals

#101

Post by eloisant » Wed, May 10, 2023, 2:55 PM UTC

moffkalast wrote: post #28

andai wrote: post #3

> I even think that joining any team is a kind of slowdown. Only by sailing alone in a small boat can one maintain agility. I'm reminded of this proverb: If you need to go fast, go alone. If you need to go far, to together.

> If you need to go far, have an AI carry you. Modernizing that proverb.

This has been true for any new tool, you can do more alone using those tools. And you can now do alone things that could only be done with a small team of people.

But still, using those tools you can achieve more with a team than alone.

Re: The Leverage of LLMs for Individuals

#102

Post by senko » Wed, May 10, 2023, 2:57 PM UTC

> Current documentation is written for human reading, with a mix of text and code blocks that makes copying a poor experience. Perhaps soon, documentation and APIs will become GPT-friendly first.

Yes.

I have recently annotated my Pydantic models and fields with the explicit intention to use the resulting JSONSchema to inform GPT how to structure some information (in effect, writing a one-off client for an internal API I'm creating).

As a happy side effect, this is now better document (information about semantics of the data structure elements is closer to the definition of the structure itself, not in some external Markdown text file or in some walled-off wiki).

Re: The Leverage of LLMs for Individuals

#103

Post by jfk13 » Wed, May 10, 2023, 2:57 PM UTC

dsign wrote: post #21

I was watching yesterday the 2006 movie "The prestige", with incredibly atmospheric locales that feel so alien. And yet, that world is but one hundred years away. It wasn't until 1934 that the Public Utility Holding Company Act recognized electricity as a utility. Less than one hundred years after that, we have managed to juice out a general digital intellect from humanity's joint efforts. Let's see if we survive the…

> a general digital intellect

That's a pretty bold claim.

Re: The Leverage of LLMs for Individuals

#104

Post by DonsDiscountGas » Wed, May 10, 2023, 2:58 PM UTC

ChatGPT has been useful to me for learning/looking-up a lot of things, although it sometimes drives me crazy. Often I'll want to use libraries which are rapidly developing, and the training data ending at 2021 kills the accuracy. A webcrawler + chatGPT would be incredibly useful. So far I've only found tools designed for the web admin (finetune on your support docs + make a chatbot for users) rather than something designed for the end user.

Re: The Leverage of LLMs for Individuals

#105

Post by Workaccount2 » Wed, May 10, 2023, 2:59 PM UTC

DonsDiscountGas wrote: post #104

ChatGPT has been useful to me for learning/looking-up a lot of things, although it sometimes drives me crazy. Often I'll want to use libraries which are rapidly developing, and the training data ending at 2021 kills the accuracy. A webcrawler + chatGPT would be incredibly useful. So far I've only found tools designed for the web admin (finetune on your support docs + make a chatbot for users) rather than something de…

I have had success just pasting the relevant documentation for using the library into the chat and telling chatGPT to reference that.

Re: The Leverage of LLMs for Individuals

#106

Post by Workaccount2 » Wed, May 10, 2023, 3:03 PM UTC

zoogeny wrote: post #82

gexla wrote: post #59

Earlier quoted context omitted.

And this is what you might say while you're learning. As you gain more experience, you realize that there's a wide range of solutions with some spectrum of a fit to your situation. A given solution may fall down in certain cases. What I love you Stack Overflow, is the context which comes with it. You get replies on a given proposed solution which point out where the solution may fail.

Step 1: Microsoft buys Stack Overflow Step 2: They implement GPT-4 responses to questions Step 3: The community + context provide the same feedback Step 4: GPT-5/6/7 gets progressively better

If they train GPT-4 to post wrong answers on the internet, and then learn from the responses, we'll have the singularity in a month.

Re: The Leverage of LLMs for Individuals

#107

Post by appleaday1 » Wed, May 10, 2023, 3:04 PM UTC

Ethan_Mick wrote: post #67

> More importantly, it gives me the courage to dream and attempt things beyond my current abilities. This is one of the small things that GPT has pushed me to do. I'm an experienced programmer and grew up playing video games, but I am not a game developer. I've dabbled over the years but can't build anything outside of a tutorial. The other day, using GPT I went through and made a Pixel Dungeon clone using Phaser (Ja…

I like how everyone has been using ChatGPT to code in Javascript, as I have done something as well.

Re: The Leverage of LLMs for Individuals

#108

Post by DonsDiscountGas » Wed, May 10, 2023, 3:05 PM UTC

Workaccount2 wrote: post #105

DonsDiscountGas wrote: post #104

ChatGPT has been useful to me for learning/looking-up a lot of things, although it sometimes drives me crazy. Often I'll want to use libraries which are rapidly developing, and the training data ending at 2021 kills the accuracy. A webcrawler + chatGPT would be incredibly useful. So far I've only found tools designed for the web admin (finetune on your support docs + make a chatbot for users) rather than something de…

I have had success just pasting the relevant documentation for using the library into the chat and telling chatGPT to reference that.

I'm talking about stuff like Bevy where the docs are scattered across multiple web pages. ChatGPT can still be helpful but typically copying/pasting a whole doc, asking a question, reading the answer, is slower than just reading the page myself. And if it's the wrong page, then chatGPT won't help.

Re: The Leverage of LLMs for Individuals

#109

Post by DonsDiscountGas » Wed, May 10, 2023, 3:06 PM UTC

bostonsre wrote: post #33

Has anyone been able to use it to effectively build more than a green field poc? It's absolutely great for that, but it's been a little clunky when trying to iterate when the context gets too large or when trying to add stuff to am existing system.

I imagine you could ask general architectural questions and it would give you general architectural answers. And then you ask more and more specific questions and get more and more specific answers.

Re: The Leverage of LLMs for Individuals

#110

Post by stevev » Wed, May 10, 2023, 3:06 PM UTC

bostonsre wrote: post #33

Has anyone been able to use it to effectively build more than a green field poc? It's absolutely great for that, but it's been a little clunky when trying to iterate when the context gets too large or when trying to add stuff to am existing system.

Domain knowledge of projects becomes effective when apps gets complex. Asking the right questions to ChatGPT will warrant you answers to help you tread unknown territory. To ask the right questions is to first understand how your app is structured, know it’s major components, what’s potentially missing. It gets technical.