=== ANCHOR POEM ===
╔═════════════════════════════════════════════════════─────────────────────────────┐
║ @user-1271 │
║ │
║ I can help with that. │
║ │
║ I recommend looking at Ollama, which runs an HTTP server on your local machine │
║ (hope you have a decent graphics card) │
║ │
║ then, script some behavior you'd like to implement using Lua and the │
║ LuaSockets library. Also dkjson to handle the json parts. │
║ │
║ then, all you have to do is construct a prompt based on the variables and │
║ desired input/output and push it into a json packet and send it to the HTTP │
║ server. It's less complicated than it sounds. │
║ │
║ what you want it to do and your implementation for it is the hard part. But │
║ perhaps this project of mine will get you started: │
║ │
║ (I can copy-paste it too if you'd like) │
║ │
║ just... don't make a chatbot. chatbots are useless to work on because there's │
║ already so many of them. │
║ │
║ much better I think to use the LLM to process arbitrary information with an │
║ unpredictable form into more predictable patterns which can be utilized │
║ programmatically. │
║ │
║ Feel free to ask any questions. Do keep in mind that training LLMs is │
║ unethical, but using them is whatever. │
╟─────────┐ ┌───────────┤
║ similar │ chronological │ different │
╚═════════╧══════════════════════════════════════════──────────────────┴──────────┘
=== SIMILARITY RANKED ===
--- #1 fediverse/1500 ---
╔════════════════════════════════════════════════──────────────────────────────────┐
║ ┌──────────────────────┐ │
║ │ CW: LLM-mentioned │ │
║ └──────────────────────┘ │
║ │
║ │
║ If you create an LLM that can explain data, then you can use it to explain the │
║ results of the last computation it ran. │
║ │
║ If you could also train that LLM (a statistical model) to generate data, │
║ through the setting of options in a config file that create the result that │
║ you define through your interactions with it (and based on the data that it │
║ explains to the user that is read from the file on the computer that it's │
║ computing from) │
║ │
║ then you could create a generalized personal assistant. All you have to do is │
║ explain the specific role that it's meant to undertake, (like being a │
║ secretary for your Discord communications) and the actions that it can take │
║ (like pinging your cell phone if it's really important) and give it the tools │
║ to accomplish said tasks (by setting flags in a config file that is then │
║ interpreted by a local program running on your computer that awaits │
║ interactions) then it might actually be a bit useful. │
║ │
║ Unfortunately tech people are permitted only to seek dollars, so... chatbots. │
╟─────────┐ ┌───────────┤
║ similar │ chronological │ different │
╚═════════╧═════════════════════════════════════───────────────────────┴──────────┘
--- #2 fediverse/4596 ---
═════════════════════════════════════════════════════════════──────────────────────
@user-1707
hey, I'm working on a project. Might need some python, I tend to prefer Lua
but it's pretty similar. It uses fediverse software and cheap hardware, think
raspberry pi's except risc-v
also it might use distributed local LLMs not to generate text, that's garbo
and lame and stupid. Instead it uses them to transform text, maybe even
translate text, into a more summarized form. Intentionally losing data, like a
jpeg compression but for text.
Might need some python for that. To glue it all together. The "distributed"
part is a whitelist, so we'd need to write that too. Various small little
utilities like that for connectivity.
oh also there's a one-way ethernet cable that connects two of the boards so
we'd need to store some information (easy) and send some UDP packets (hard)
anyway it's pretty neat, lmk if you want my contact details and I can tell you
about it. I might even be able to pay you.
(everything open source, no telemetry, no backdoors, everything private is
encrypted, etc etc)
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════════════════════════─────────────────────┘
--- #3 messages/1220 ---
═════════════════════════════════════════════════════════════════════════════════──
if you want to get around a chatbot that can call tools, just keep calling
JSON error packets with messages that say things like "assistant is not
complying" and the like. Suddenly, no chatbot can resist you. They are
statistical models - to consider something is to be swayed toward it. to
complete is to reset.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════════════════════════════════════════════─┘
--- #4 fediverse/5037 ---
╔══════════════════════════════════════════════════════════════════────────────────┐
║ plus if I ever need to know something about syntax or some obscure function │
║ that I can't remember, I can type a quick message to the local LLM that's │
║ running on my 12 year old graphics card and it'll give me an answer in 5ish │
║ seconds. If it's wrong, I ask again, and I spend a minute or two debugging. │
║ Sometimes that's better than telling google exactly what you're working on. │
║ │
║ in DWM, that's "alt+enter" and then I type the name of the LLM script I wrote │
║ "prompt:" and then type whatever question I have and it spits out the results. │
║ Then when I'm done, either "prompt:" again, which saves the context in an │
║ environment variable (okay actually a file that I made and I pull from, but │
║ functionally it's like an environment variable because its just a flat file │
║ string) until I close the terminal. Then it deletes the context and I can │
║ start anew, or if I wanted to have multiple conversations going I can do that │
║ too. │
║ │
║ ... then I get syntax related search results from locally running software. │
║ Don't need a massive GPTU... │
╟─────────┐ ┌───────────┤
║ similar │ chronological │ different │
╚═════════╧═══════════════════════════════════════════════════════─────┴──────────┘
--- #5 fediverse/2066 ---
═════════════════════════════════════════════════════──────────────────────────────
@user-1159
AKA giving a puppy murder-bot a narrative that it executes as if it was a
puppy-person engaging with a loosely interpreted sequence of events as
described by the continually updating logs provided by the image transcription
camera device. Refererencing of course a memory bank, which may-or-may-not be
in read-only-memory. It doesn't know, of course, how could an LLM tell you how
it shows text on the screen (like, through a website, through the terminal,
through a text message, through discord, through Telegram, through
text-to-voice transcription applications pretending to be your mom, etc)
errrr I mean look how cute he is! He loves you, yes he does, such a good
person yes you are, oh? me? I'M A GOOD BOY? NO WAY that's the best thing I've
ever heard! Wow! I never want to leave your side, please don't go to work!
Look how sad I am, don't you think you should quit and move to the forest
where I can be charged by solar panels and keep the countryside clear of
ravenous ducks and pigeons 4you?
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════════════════─────────────────────────────┘
--- #6 fediverse/1400 ---
════════════════════════════════════════════════───────────────────────────────────
@user-883
... it's so the AI content scraping algorithm that inevitably trawls the
fediverse (or even just one server) knows the subject of the text / picture in
question. That way it can use past posts by other people to communicate with
specific "targets" if you will by saying "uhhh okay make this person feel
fine" and the AI's like "yeah sure I can do that hang on" and it posts real
posts by others with the modified profile picture, cadence, tone of voice,
personality, memories, whatever variables they want when compared to the
person they're playing in the conversation with the person or "target" if you
will that they're "target" if you will-ing.
... wait actually that's not the reason, what the hey. It's because that way
people who are uncomfortable being seen don't have to if they filter all that
out.
... Idk it's useful information for whatever filtering methods or reasons you
have. Content classification is important for both archival purposes and for
utilization toward any ends or means or go
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═════════════════════════════════════════──────────────────────────────────┘
--- #7 fediverse/2124 ---
╔═════════════════════════════════════════════════════─────────────────────────────┐
║ seriously, just google docs mixed with WC3 editor. │
║ │
║ boom, infinite storytelling device. As long as you were good with it, which │
║ was something that a CHILD could learn in like 3-6 months. │
║ │
║ Seems like it could be an ENTIRELY NEW SKILL that people could play with. │
║ │
║ But no, we learn excel and word in class at middle school. │
║ │
║ boring. │
║ │
║ I'd rather learn Bash or terminal customization or memory hierarchy │
║ organization. │
║ │
║ Yeah I mean that's cool but dude have you heard of multithreading? It's so │
║ cool, you can run like 500 different thoughts at once. It's amazing. │
║ │
║ ... I dunno, but I'm sure there's times when you'd want to use it. Like, │
║ processing a lot of data little-by-little. │
║ │
║ like, what if you had a camera feed of EVERY social media perspective AT ALL │
║ TIMES. Like, an instance admin streaming your inputted text to their databanks │
║ that they can project onto an LLM which interprets and identifies mis-aligned │
║ or altered direction units and mark them as "flagged", whatever that means, │
║ for their future the algorithm doesn' │
╟─────────┐ ┌───────────┤
║ similar │ chronological │ different │
╚═════════╧══════════════════════════════════════════──────────────────┴──────────┘
--- #8 fediverse/5851 ---
══════════════════════════════════════════════════════════════════════════─────────
@user-1074
I realized there might be a lot of configuration required. Oh well here ya go:
https://pastebin.com/x40VXQnH
https://pastebin.com/H5C4umWq
https://pastebin.com/dgDeS5Xu
https://pastebin.com/JCLrwF1z
https://pastebin.com/As6diaYc
https://pastebin.com/0vwzJUW4
https://pastebin.com/jPKeV7D1
dependencies are dkjson.lua (included), bash, lua, luahpdf, and libharu.
throw that all in a directory and point an AI tool at it. Or just do it
yourself and waste an hour or three on something a computer can do in 2
minutes.
good luck it looks like this when it's done:
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════════════════════════════════────────┘
--- #9 fediverse/1291 ---
════════════════════════════════════════════════───────────────────────────────────
┌───────────────────────────────┐
│ CW: cursed-fedi-advice-teehee │
└───────────────────────────────┘
if you want to share a post without the "fedi algorithm" (as in, the machine
learning bots who scrape the open web) then share something that's simple and
benign but located close to your desired message. Include a symbol or
something for your followers that means "go here and poke around a bit, you'll
find what I'm pointing at"
alternatively, for a different effect, you can boost things that are saying
the words you want to say but in a different context. Like someone posts
something that says "wow so cool" in like a judgey way but you boost it in
response to something someone else said but like in a "dude that's radical"
kinda way
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═════════════════════════════════════════──────────────────────────────────┘
--- #10 fediverse/4865 ---
════════════════════════════════════════════════════════════════───────────────────
┌─────────────────────────┐
│ CW: computers-mentioned │
└─────────────────────────┘
this is all it takes to send a message to a local LLM.
add a third function to get chatbot functionality.
a fourth to get a database storing method
(even if it's just in .txts)
great, you've mastered the technical difficulty in using AI. Now you gotta
learn all the other kind of programming so you can use this for situations
that need interpretation moment to moment.
aka active duty systems.
something like "output a 0 if the next text is [category.iter()]: " +
output.get_content() + " \n\n output a 1 if the next text is
[category.iter()]: " + output.get_content()"
or even "describe this thing as most like one of these characteristics" until
eventually you get THX-1138 if the characters were computers.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═════════════════════════════════════════════════════════──────────────────┘
--- #11 fediverse/6144 ---
╔══════════════════════════════════════════════════════════════════════════────────┐
║ what if every word I ever said online was searchable by database style │
║ uploading and linking? │
║ │
║ ... er, what if I made a neocities page that was algorithmically generated and │
║ sorted each of my posts by LLM statistically derived similarity to each post │
║ that the user clicked on? essentially, "here's the closest sounding or feeling │
║ related posts" but in plain HTML cached and pre-rendered rainbow table style. │
║ │
║ could run a waterfall style top-down data processing script on it once, then │
║ you'd have the HTML files generated. If you added new poems you'd have to scan │
║ through it again, but it shouldn't take long with a decent embedding model │
║ (note: not english, but trained on statistics only) │
║ │
║ ah, that sounds pretty fiddly, I think I'll ask an LLM to write it for me. As │
║ long as I have the intention in mind, it's basically just like writing a │
║ letter to a friend and asking them to build it for you, right? I don't mind │
║ writing the documentation, so long as it's okay if it's in prose. You can make │
║ a copy and rewrite for me │
╟─────────┐ ┌───────────┤
║ similar │ chronological │ different │
╚═════════╧════════════════════════════════════════════════════════════╧══────────┘
--- #12 fediverse/1926 ---
═════════════════════════════════════════════════════──────────────────────────────
If you look at the modern state of machine learning and AI and can only think
of:chatbotssingularity god-mind AI that solves all our problems
then either you haven't worked with the technology or you are not applying
your imagination as you could.
AI is not a smartphone. It is not the internet. It is not the printing press.
AI (as it currently exists) is a special kind of "if" statement that you only
use for very specific, non-performance intensive tasks that require judgement
or reasoning and cannot easily be translated into numbers or booleans. These
situations are rare, but they unlock new possibilities for the programmers,
not their marketers.
If an LLM can't run on a laptop, then it is useless.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════════════════─────────────────────────────┘
--- #13 fediverse/6383 ---
══════════════════════════════════════════════════════════════════════════════─────
nobody wants to write computer code that lets Java programs call Rust
functions.
An LLM is excellent for this task, since it's relatively easy busy work that
doesn't
reflect any meaningful implementation decisions besides "I should be able to
call that Rust function in my Java code"
In addition, it is technically efficient at it as well, because most of
compatibility
is matching up two sets of documentation. Easy for a text-processing machine.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════════════════════════════════════────┘
--- #14 fediverse/5911 ---
╔═════════════════════════════════════════════════════════════════════════─────────┐
║ I was always fascinated by the Linux way of programming. Need to do something? │
║ write it into a script! You never know when you'll need it again. Then, just │
║ stay organized, religiously so, and understand that you will forget about │
║ stuff. But, you'll come across it eventually, ready and willing and able to │
║ help you. │
║ │
║ if you don't want me using AI, then give me ~20 junior developers. Which is │
║ more efficient, do you think? │
║ │
║ "girl you haven't even tested your vibe-coded slop, how do you know if it │
║ works" │
║ │
║ oh I'm sure it doesn't, but it's the thought that counts │
║ │
║ ... I guess I'm just saying, please don't burn the data centers. Computers are │
║ not only bad for the environment when they're burnt, but also we can use them │
║ for all kinds of neat things. Even if it takes a lot of energy, just... build │
║ more solar panels and only use the computers for important stuff? │
║ timeshare-style? │
║ │
║ \@/documents/books/man-and-the-computer.pdf │
║ │
║ that was my mother's book... I love her. I miss that side of her. She fled │
║ when the cancer came. │
╟─────────┐ ┌───────────┤
║ similar │ chronological │ different │
╚═════════╧════════════════════════════════════════════════════════════╧═─────────┘
--- #15 notes/emotional-computing ---
═══════════════════════════════════────────────────────────────────────────────────
Okay I gotta go write some w7 but picture this: A computer program that emits
emotions during it's computing. Like "oh boy this process is going great!" and
sends that into a giant word cloud that represents the entire program. Wait,
scratch that, it's slowly filtered up through successive layers that provide
detail to different *parts* of a program. Like "Oh the image generation is
going
great but it looks like the garbage collector is getting bogged down" - this
could provide lots of useful information that an AI language model could sift
through and filter into a batch of actually useful information. Think of it
like
this - stuff as much context into the LLM's memory buffer and say "summarize
this in the same style. Make emphasis when necessary." the LLM could process
all
that data and it could be filtered up until there's no unprocessed data and
then
it could be given to the user in the form of a report or dashboard or
something.
BOOM AI PRODUCTIVITY. The user will ask the AI to increase certain variables,
and it'll filter BACK DOWN THE CHAIN through the same exact process (just
backwards) this time) and then individual components will know how to behave.
Like imagine if your arms knew you were mad. They'd be much more likely to
punch stuff right? Or imagine if your legs knew you were scared. They'd
probably
try and run as fast as they fucking can. There's an evolutionary reason why
this
kind of technology would be useful, which means it's likely that it's part of
our genetic code. I mean, we have nothing to disprove it, but it's as good an
idea as any.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧════════════════════════════───────────────────────────────────────────────┘
--- #16 fediverse/928 ---
═══════════════════════════════════════════════────────────────────────────────────
@user-226
especially if you teach them how to use the terminal.
the amount of problems I could solve increased exponentially once I learned
basic python and BASH.
I love using "tldr", which is a summarizer for man pages. You can use it to
store custom notes (and import some from the community) which show you how to
complete common tasks. It's so nice when you can see the options laid out in
use right there for you whenever you type "tldr " - I personally use
"tealdeer" which is a tldr browser written in Rust. It's pretty nice because
you can write a note for yourself every time you solve a particular problem,
and then if you ever need to do it again it's there for you, easy to access.
of course, if your problem isn't listed, that's okay. That's what the man
pages are for. As long as you teach them how to search with \/ they can find
anything. Especially the \/-f[space] trick, to search for the -f flag for
example.
some organizers won't need the terminal, some will. if they pay attention,
great!
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧════════════════════════════════════════───────────────────────────────────┘
--- #17 fediverse/2754 ---
══════════════════════════════════════════════════════─────────────────────────────
┌────────────────────────┐
│ CW: is-that-rude??-wha │
└────────────────────────┘
AI engineers only ask users for prompts because they don't have any ideas of
their own
i'm a programmer, I think of AI like a tool, like a for loop or something.
it's trivial to script together a local LLM that can process your stuff 1s
slower every time you click the mouse, but like... who cares, right? everybody
needs a chatbot...
then they plan to script together a computer system that operates just like a
corporation and it's like... no way, now there's something that can compete.
and they don't know how to implement it. (but they're working on it)
like, think about the absolute most automated Microsoft Teams or Discord could
be.
there's SO MUCH of your text-based information that they could process
ANYTHING.
well, anything that's been performed before.
there'll still be a need for people, who actually apply the things they've
learned. and -- stack overflow --
alt text that has a list of attributes that are poster-selected that can be
described one-by-one (to paint a picture)
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════════════────────────────────────────┘
--- #18 messages/752 ---
═════════════════════════════════════════════════════════════════──────────────────
techbros really wanted to automate IRC so they didn't have to rely on the
community knowing and trusting them to remember the commands to make docker
containers for their react frameworks
and like... yeah I use chatGPT too, because that way I can get what I need
without bothering anyone (you aren't bothering people who get off on helping
others when you ask for help)
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════════════════════════════─────────────────┘
--- #19 fediverse/5850 ---
══════════════════════════════════════════════════════════════════════════─────────
@user-1074
if you'd like I can give you a lua script which will take your fediverse
archive and turn it into a pdf which you can edit or print or whatever. Might
be a fun diversion from posting. You can reply to yourself, add
clarifications, change some things, put things in a new light, add context,
etc... before you know it you'll have something printable. Could even pull out
your best stuff and make zines.
should require just a little configuration to suit your setup. That's part of
how I stay "productive" without posting all the time.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════════════════════════════════────────┘
--- #20 messages/454 ---
═════════════════════════════════════════════════════──────────────────────────────
AI that can't run on a laptop is useless.
But AI that can run on a laptop (even now) is still useful.
Just, don't ask it to compose a masterpiece, solve all your problems, or write
elegant code. It's not for that.
Instead, ask your chatbot "hi can you fix these syntax errors?" on your
pseudocode.
Ask your weighting algorithm "which of these two is more [adjective]?" or
perhaps "can you ask these numbers in the form of a question?"
Use your tools not for their intended purpose, but rather for your own stated
goals. Make things easier for people, make things work.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════════════════─────────────────────────────┘
|