I really want to use AI like llama, ChatGTP, midjourney etc. for something productive. But over the last year the only thing I found use for it was to propose places to go as a family on our Hokaido Japan journey. There were great proposals for places to go.
But perhaps you guys have some great use cases for AI in your life?
A lot of translation and summarisation. ChatGPT is extremely good in absorbing a whole mix of comments in different languages and summarising them in English (or whatever other language).
For programming I don’t use it so much anymore because it hallucinates too much, calling APIs that don’t even exist. And when I lower the temperature the output is too sparse.
I’m also trying to build an assistant that can also communicate proactively (I intend to auto-prompt it when things happen and then evaluate if it should cause a message to me). But I need to get a local LLM going for that because running that through the ChatGPT API will be too costly.
Also, a replacement for some of my web searches. Sometimes I just want to know something and it’s refreshing that it can give me an answer (even though it does need to be validated, it’s much easier to do that when you know what you’re looking for!)
I’ve used it to make specific images for work proposals that stock sources may not have. Sometimes for fun, I vary it so it’s in the style of a cartoon or a Japanese woodcut.
I use it to see the answers to problems on my physics homework when I can’t figure it or myself. It works far better than forums, which are mostly all paywalled these days.
If you are using ChatGPT for academic purposes, start your prompt with “pretend you are an expert professor on {subject} helping me understand {topic}”
Both of you need to read up on the phenomenon called hallucination.
LLMs can be great for explaining things that have concrete solutions, like physics and math problems, when they have a separate “computations” AI bolted onto it, like ChatGPT does. Usually, you can check the answer in the back of the book anyway, so it’s very easy to catch fact hallucinations.
I wouldn’t worry about source hallucinations with this either. I don’t think it would even come up?
I don’t. Played with it a bit but as a capable writer and coder I don’t find it fills a need and just shifts the effort from composition (which I enjoy) to editing and review (which I don’t).
Mostly the same. I tried ChatGPT a few times to get it to generate some code, but mostly it produced code that didn’t even compile and when I asked it to fix it, it created code that didn’t compile in a different way. I enjoy writing code on my own a lot more than having to review some pre-generated code.
Though I use it as a glorified Google sometimes and that is not even so bad.
I use them mostly for
- practical ideas on things that I can reliably say “nah, this doesn’t work” or “this might work”. Such as recipes.
- as poor man’s websearch, asking them to list sites with the info that I want.
Enhanced googling
I’ve been making a small album of music out of lyrics I wrote and a consistent general style/genre using suno. It’s pretty fun.
As a musician with experience recording albums, even when the songs come out basic, I can always re-record them myself and make them less generic.
Almost nothing. I sometimes use it to rephrase a question or answer. I refuse to become dependent on AI or contribute to it more than I already unwittingly have.
I use it to generate code documentation because I’m incapable of documenting things without sounding like a condescending ass. Paste in a function, tell it to produce docstrings and doctests, then edit the hell out of it to sound more human and use actual data in the tests.
Its also great for readmes. I have a template that I follow for that and only work on one section at a time.
I use it for exactly the same thing.
I used to spend hours agonizing over documenting things because I couldn’t get the tone right, or in over explained, or some other stupid shit.
Now I give my llamafile the code, it gives me a reasonable set of documentation, I edit the documentation because the LLM isn’t perfect, and I’m done in 10 minutes.
Over-explaining is my biggest issue. I’m entirely self taught and the trash quality of certain softwares with non-descriptive variable and function names sort of steered me towards clearly naming things (sometimes verbosely). That has the unfortunate side effect of repetition when documenting and it comes across as sarcastic or condescending when proofreading.
Its far easier to have a machine do it than to second-guess every sentence.
You mentioned a llamafile, is that offline? I’m using GPT-4 at the moment because my partner has a subscription. If so, I maaaay have to check it out ^^
Its also great for readmes. I have a template that I follow for that and only work on one section at a time.
Templates in sections are somewhere where it shines. I set up a template for giving information about a song – tempo, scales used and applicable overlapping ones, and other misc stuff. It’s really nice for just wanting to get going, it’s yet to be inaccurate. It’s quite nice, having a fast database that’s mostly accurate. I do scrutinize it, but honestly even if it were to be wrong one day, it’s just music and the scale being “wrong” can only be so wrong anyhow.
Nope, nothing. There doesn’t honestly seem to be anything I’d use it for, even then I wouldn’t wanna support it as long as it uses Data its gotten by basically stealing. Maybe once that has gotten better I’ll look more into it, but at the current moment I just don’t have the heart to support it
Copying is not stealing. It’s corporate propaganda conflating the two.
It is stealing lots of potential work and income from professional creatives, though.
Improvements in technology do not guarantee employment for tradespeople of current technology. A whole lot of horses became unemployed when cars became ubiquitous. I’d say the improvement of cars to society is worth the loss of employment to all those who maintained the horse’s infrastructure. Like all those manufacturing jobs lost from the improvement in machines, professional creatives must adapt to the times, or seek other forms of work. No different than any other job in all of history.
But the difference I think is this isn’t just affecting a few niche industries (horses, carts and their associated care). AI is going to replace a huge, huge chunk of the workforce with no new jobs created to replace them. Even in the industrial revolution there were new jobs created - shittier jobs, but jobs. This is different.
Which is exactly the same as how there were no new jobs for horses created. Employment is not a right. You have to either adapt with the changing times, or become unemployed. I agree that it sucks.
Employment is not a right? Well if we continue with a capitalist system and give most people no way to earn a living, we will need something to replace jobs for most people. We should not merely accept that it sucks and let things go to shit. We could pass laws limiting the use of AI or protecting workers, or providing basic income…
Whatever we do we had better figure it out soon, though.
100% agree. Universal Basic Income feels inevitable as a solution. Better and better technology puts machines in place of human labor, with no guarantee that other jobs will come into existence to replace the ones lost. Is it not the ideal goal to have machines do all labor, leaving humans to do what they actually want without fear of homelessness and starvation.
It just kinda sucks right now because these systems don’t exist to support this changing landscape.
They take what we make, be it art or Text without our or anyones consent, to me thats stealing something. And yes, there are AI Tools fully build on public Domain and open source things, but those are at the moment, few and far between.
They use them but they don’t take them. If I steal your bike, you no longer have a bike. If I copy your bike, you still have your bike.
I’ve only used DuckDuckGo’s implementations of GPT and Claude. I haven’t really found a use case yet. I don’t trust it enough to for queries related to things I don’t understand (gaps in my knowledge) and would rather solve these problems or learn these skills through exisiting sources of information that I know have had at least some level of human refinement/vetting. Personally I enjoy the challenge of problem solving in life, particularly when the solution involves learning a new skill that I can utilise again in the future. I find it interesting that AI is advertised as being able to maximise our capabilities as humans, because it appears to be used for the complete opposite in most cases. People want to use their brains less and just be spoonfed the answers.
The only practical thing I have found I can do with AI is brainstorm ideas (or rather expand upon little ideas I have but don’t know where to go after) or figure out what’s wrong with a snippet of code when I can’t figure it out on my own.
I pretty much only use it for brainstorming ideas.
Mostly for finding information that for whatever reason can be difficult to find using search engines. For example, I’ve used ChatGPT to ask spoiler-free questions about plot points in books I’m reading, which has worked rather well. It hasn’t spoiled me yet, but rather tells me that giving more information would be a spoiler.
Last time I tried to look something up on Google, carefully, I got a massive spoiler for the end of the entire book series.
I also use it for code-related questions at times, but very rarely, and mostly when using a language I’m not used to. Such as when I wrote an expect script for the first (and perhaps only) time recently.
So many times I wanted to know the name of an actor who played a character after the first episode and the top result was something like “[Character Name] (deceased)” or " Villain: [Character Name]."
I don’t and the energy consumption of public AI services is a stopper for “testing and playing around”. I think I’ll just wait until it takes over the world as advertised.
I would argue they already have. Just as cars used to be slow, inefficient, and loud, compared to today. Overtime their will inevitably be improvements in how they run, but also improvements in dedicated hardware support. Timeline wise, we are enjoying the hot new Model T, knowing eventually we will get to have a modern Honda Civic.
