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

The Leverage of LLMs for Individuals

mazzzystar.github.io

Post reply on HN
Print view View original

231–240 of 311 posts

Re: The Leverage of LLMs for Individuals

#231

Post by valine »

IshKebab wrote: post #226
spudlyo wrote: post #217

Earlier quoted context omitted.

Give the LLM access to `shellcheck` and have it iterate on the warnings. I think promising results have been shown when you allow LLMs to reflect on their answers and give them access to tools.

Shellcheck can't check everything though. I think using LLMs on difficult to verify code like shell scripts and complex regexes is a pretty bad idea. I've found them useful as a "smart search engine", e.g. if I don't even know the magic terms to search for. Most of the time it gives me answers that are completely wrong, but are close enough that I know where to look to find the right answer. E.g. "Using the rapidchec…

Depends entirely on if the shell script is mission critical. I couldn't care less about the quality of my LLM shell scripts most of the time. My only success criteria is that is that it solves a problem. These are scripts I'm never going to touch again, things like batch converting files, or like one time I had it generate a script to titrate stable diffusion parameters. As long as I can skim the output and see that its correct I'm happy.

You call it a bad idea, but it's saved me hours of work.

Re: The Leverage of LLMs for Individuals

#234

Post by zackmorris »

Semi-serious question: how do we help those too old to begin the training?

When I went through profound burnout in 2019, the part of my brain that handles planning and execution shut down for about 6 months. I could barely get out of bed, brush my teeth, etc. The grieving process was rough, as well as the struggle to relearn how to function in a culture that doesn't allow breaks. And it was physical, perhaps brought about by sleep apnea and digestive warning signs from stress that I ignored. I survived by separating the planning from the doing, by keeping todo lists and forming habits over weeks that began to rebuild the wounded parts of my psyche so that I could task and adult again.

I've since regained my executive function, but the experience changed me. The stuff that used to be automatic became manual, so work takes an even higher toll than it did before, and may even even have all-consuming qualities. I feel, institutionalized, like Brooks in Shawshank Redemption.

I know that AI offers a way to automate much of the doing, and within 5-10 years the planning as well. All I have to do is use it. But I'm just so tired physically, mentally and emotionally that the potential benefit feels like a burden. I struggle profoundly to make long-term plans or deal with the logistics around that. I will almost certainly miss this wave of innovation, just like I missed the VR, mobile and gaming bubbles before that. Living my most laborious life instead of my best life.

What I'm feeling deep down is that this time is different. AI should not be about personal empowerment. It should be about lifting others who are too infirm after a lifetime of hard work to do it themselves, so that they can rejoin the human race and make the contributions in their hearts that fulfill the promise of their self-actualization. I just don't know where to go with that sentiment, or if my feelings are even relevant anymore.

Re: The Leverage of LLMs for Individuals

#235

Post by wccrawford »

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'm trying to visual the process you're using for this, and it's just not coming to me. Can you give me a run-down on it, or point me somewhere that has one?

Re: The Leverage of LLMs for Individuals

#236

Post by georgehotelling »

vemv wrote: post #40

There's a long gap from: I built a podcast search website to: Staying in any company right now is a negative return. We humans are too easily impressed by tricks, and are too willing to extrapolate them to fantasy land. GPT can certainly accomplish an impressive variety of small tasks. Whether it can build large-scale systems that will power tomorrow's world is uncharted territory. Can you build something meaningful,…

It's worth noting that the podcast search website makes request to Apple's podcast search API, then formats the results.

I would be interested if OP could glean enough from GPT to build the search index as well, a much more complicated project.

Re: The Leverage of LLMs for Individuals

#237

Post by spaceman_2020 »

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 taught myself to code just to build a prototype of an app I wanted to create. My plan was to launch the prototype, get some market feedback, and then find a technical cofounder or hire someone.

It took me 8-10 months of learning to build a prototype. But then GPT-4 came along and I could suddenly ask it questions about features I wanted to add. I then realized that there were so many features I could build on my own.

It has made me far more ambitious as a noob programmer.

Re: The Leverage of LLMs for Individuals

#238

Post by jvanderbot »

ska wrote: post #208
rounakdatta wrote: post #188

Earlier quoted context omitted.

> If you can make something using AI, so can everyone else The idea / creativity is hence the key. Novel ideas don't occur to everyone.

Not really. Ideas have always been cheap. They occur to everyone. Most of them aren't great, let alone good. But good ideas, even great ones, rarely mean much on their own. It's always been execution.

Well you need both, a great idea and great execution. I agree with your sentiment though that execution (and timing) are the differentiation.

Re: The Leverage of LLMs for Individuals

#239

Post by hansvm »

martinflack wrote: post #183
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…

Given the token count limits on input and output, I've been wondering how folks work on these long-running projects? Is it just not a problem, or are there some tactics? I find in trying to build up lengthy outputs that it starts truncating or leaving out things from way before.

I use the API and have a generic prompt prefix for each programming language and type of task to try to get as much bang for my buck with as small of a token count as possible, and then tossing in a single query with a bit of project-specific code fleshes out the rest of what I'm asking it. Prompt tokens are usually around 300-1000, leaving over 3000 for the response (which it rarely fully uses).

It's garbage at pulling in things from all over the codebase, so as a sort of co-evolution I write code that mostly only needs local context and only ask it questions that only need local context. That works great at home but doesn't suffice on the existing code at $WORK.

It's still helpful here and there at work (e.g., given this example string please output the appropriate python datetime formatting codes), but only because it's a wee bit faster than synthesizing the relevant docs and not because it's able to consistently do anything super meaningful.

Re: The Leverage of LLMs for Individuals

#240

Post by blibble »

collaborative wrote: post #57

AI tools are absolutely useless once you get past any initial stage in a software development cycle They just can't comprehend what needs to be done even if all that's required are 2 lines of code However, we keep seeing posts from people who don't know html or how to create a chrome extension paternalizing about how we can be much more productive with AI tools. Last I heard a CEO was demanding dev increased producti…

> Last I heard a CEO was demanding dev increased productivity or firing some devs because he saw a Youtube video about how easy it is to create a website now

reminds me of Donald Trump complaining about the health exchange website costing millions of dollars when he can build a website for $3

Post reply on HN