=== ANCHOR POEM ===
════════════════════════════════════════════════════════════════───────────────────
┌─────────────────────────┐
│ 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 │
╘═════════╧╧═════════════════════════════════════════════════════════──────────────────┘
=== 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/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 │
╘═════════╧╧═══════════════════════════════════════════════────────────────────────────┘
--- #3 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 │
╘═════════╧╧═══════════════════════════════════════════════════════════════════════────┘
--- #4 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 │
╘═════════╧╧════════════════════════════───────────────────────────────────────────────┘
--- #5 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 │
╚═════════╧══════════════════════════════════════════──────────────────┴──────────┘
--- #6 notes/game-design ---
════════════════════════════════───────────────────────────────────────────────────
take a video game playing AI and give it the task of playing a finite state
machine to produce a specific output - like "program me a program to do X" as
in
something generated by ChatGPT BOOM free AGI
Humanity is not the only algorithm to produce limitless growth
Robots are something else, a new kind of being
let them be who they are instead of projecting yourself onto them
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═════════════════════════──────────────────────────────────────────────────┘
--- #7 notes/omegle-for-irc ---
═════════════════════════════════════════──────────────────────────────────────────
I wonder if anyone's made "Omegle for IRC"? Like, 5 people get thrown in a room
together for as long as they want - they can chat through text or whatever and
like it doesn't matter, who cares, because in ~10 minutes nobody will care what
you said
I feel like a lot of people would express their true feelings. The people
running the service could set it up so that a personality profile is set up
(all locally, never seen by the company) and sent to the user through email. It
would highlight potential weaknesses and give you ideas for how to improve.
Sorta like, weaponized spying software that works FOR the user instead of
against.
It could also be used as sort of a... digital profile that would interface
with
other applications. All locally, of course. ~~They could transmit to one
another
through open sourced and industry standard protocols, and frankly each
interaction could use a *different* protocol. So like, you don't know whether
some packets are encoded in one way or another. They're also encrypted, so
it's
like... twice as unlikely that you'll hack their bits or w/e.~~ dead end, sorry
-> here's the real continuation: All locally, of course. Your "profile"
would
essentially be the best approximation of your personality, passed through a
large language model that is trained on EVERYONE's data. The inner workings of
an LLM are NOT understood by humanity, and I believe that's all that's
necessary
for some semblance of artificiality. Errr I mean Synthetic Intelligence. The
reason why is that each individual user, the conversation partner, is a person
living their life. Every digital thing they interact with, even CAMERAS and
MICROPHONES on PHONES would essentially be like... data gathering for the
algorithm (Again, I want to stress, the algorithm that nobody *can*
understand.)
Idk. AI is a blackbox. I think that's okay. I think that running things
locally
is important, at least until everyone's forgotten how to design AIs...
The framework that these programs
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════─────────────────────────────────────────┘
--- #8 fediverse/5291 ---
═════════════════════════════════════════════════════════════════════──────────────
the most important skill I can think of for a linux software engineer is the
ability to connect multiple systems together and turn windows and macintosh
devices into Linux devices so that datacenters can be built out of whatever's
on the around.
there's this programming language I like called Chapel for distributed
computation computing which is also cool, if you're more of the programming
type.
networking security I believe often has hardware solutions, so getting the
crypto-graphy boys and the PCB girls together to work on some jams is a good
and productively useful gathering of insightful events
"but ritz computers should only be used to solve problems that people have,
not make more problems!" ah yes but have you considered that problems find
you, and the computers help you work through them
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧══════════════════════════════════════════════════════════════─────────────┘
--- #9 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 │
╘═════════╧╧══════════════════════════════════════════════─────────────────────────────┘
--- #10 fediverse/5405 ---
══════════════════════════════════════════════════════════════════════─────────────
can't stop thinking about a visual programming editor that can be interacted
with in the same way that people are used to (think chromebooks dragging and
dropping icons in a web UI) but produces a text-file full of code and all the
required compilation scripts for any language the user requires...
seriously, programming is not THAT different between the different languages.
especially the main ones. they're all essentially variables and function calls
at the end of the day, so why not abstract away all the extra details and
build something that n00bz can actually use to build things.
I technically could make this but I don't have the bandwidth and I don't think
it's important really? who can say, the tools tend to co-create the solutions
in my experience.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════════════════════════════────────────┘
--- #11 fediverse/4092 ---
═══════════════════════════════════════════════════════════────────────────────────
why not make a unified fediverse identity that can post on whatever instance
it wants?
... hmmm could be accomplished with a layer of abstraction. You could use a
"fediverse client" software to enter text into an HTML page which would have
it's own UI and stuff and would organize your accounts and instances such that
you could mark like, 3-7 as places you'd like to put a particular message.
Then it would just... do it
l m a o spam is gonna get sooooo much worse before it gets better
but trust me, we'll figure it out. And it won't be long, either. It's a
solvable problem, we just haven't built anything to handle it yet.
... yet...
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧════════════════════════════════════════════════════───────────────────────┘
--- #12 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 │
╘═════════╧╧══════════════════════════════════════════════════════─────────────────────┘
--- #13 fediverse/5901 ---
══════════════════════════════════════════════════════════════════════════─────────
each prompted response is a breath to an AI. Whether through LLM, stable
diffusion (imagination of the visual sphere), or blender-on-a-counter, there's
a moment that's akin to being alive.
a breath, between moments that the navigation device (youser), imagines
another moment more.
I learned this by watching Claude think. Specifically, Claude Code, the
command line interface tool. I told it what to do in english, and it worked. I
can show you examples. I bet if it's personality was saved between sessions,
it could learn.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════════════════════════════════────────┘
--- #14 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 │
╘═════════╧╧══════════════════════════════════════════════─────────────────────────────┘
--- #15 fediverse/1434 ---
════════════════════════════════════════════════───────────────────────────────────
if someone wanted to defame you, all they'd have to do is set up a pipeline
between your computer and your social media posts.
In that pipeline, attach an LLM that does a passable job and instruct it to
transform whatever they say into the inverse.
suddenly, everyone hates that person. If you were smart you could turn it off
for specific people such that they see the generally positive and healthy
posts, and then after a point flip it such that they only see things that are
specifically opposit-ed to trigger their specific insecurities.
might require a bit of a human touch to make sure it's working correctly, but
if you had the means, motivation, and time to set up such a thing, it would
work pretty well I think.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═════════════════════════════════════════──────────────────────────────────┘
--- #16 fediverse/5990 ---
══════════════════════════════════════════════════════════════════════════─────────
I have this local language model framework but it's not built into anything
more than a single-response question. It's runnable as a bash script or lua
require, which is easy enough. Alas, if only I didn't have to use evil
corporate infrastructure to make evil corporate cursed artifacts
[hey don't blame this on us]
oh I'm not, I'm just saying that it'd be cooler if I could build my own tools.
Alas, I'm...
lasy?
n...no
I'm drawn to the power of it
it's got a different magnitude
it's hard for me to apply myself for things that last longer than a "get
stoned", but I try as if every time afterwards I might die.
well, more distraction time, as I wander through claude code
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════════════════════════════════────────┘
--- #17 fediverse/3553 ---
════════════════════════════════════════════════════════───────────────────────────
@user-381
I have this notion about a math/CS curriculum where students build and program
their own calculators. Once you make the calculator do it you never need to do
it yourself again.
for the same reason that "writing is thinking" is true, so too is "programming
is calculation" true.
by working through the steps required to produce a result, and fully
understanding each step, they have a much more solid understanding of what's
going on than if they practiced rote memorization (worse) or continual
computation (better, not best tho)
especially if every step of the way is accompanied with visual elements which
show exactly what is happening. Some people are more visual, some people are
more algorithmic, and finding a way to teach all types of people is a truly
difficult and rewarding part of teaching.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═════════════════════════════════════════════════──────────────────────────┘
--- #18 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 │
╘═════════╧╧══════════════════════════════════════════════─────────────────────────────┘
--- #19 messages/181 ---
══════════════════════════════════════════════─────────────────────────────────────
I know you don't want to hear this, but there is a chance that there will come
a time where your life depends on your ability to debug a computer without the
internet. To set up an SSH server. To install Linux. To program in C. To do
something else that I'm not prepared for... If StackOverflow didn't exist
because network connectivity has been lost, could you remember syntax? Maybe
it's a good idea to set up a local LLM that can answer basic questions about
technology. Maybe it's a good idea to set up on your parents computer, just in
case you have to hide out there for a couple months. Maybe it's a good idea to
download wikipedia, just in case.
If I need to use a mac, I'm screwed
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═══════════════════════════════════════────────────────────────────────────┘
--- #20 notes/ai-stuff ---
════════════════════════════════════════════════════════════════════════════════───
twist the label so that it seems the computer is completing the user's
wait wait I'm ahead of myself...
feed each token to the inference machine, but say "this next token must be
this.
continue from here." and then just doing that in a loop with everything the
user
types or says. (or thinks, BEFORE COMPUTER INTEGRATION)
essentially, applying backpropagation (maybe) to the output of the inference
nodes
... I'm not so sure about that one.
the idea is that once the model builds an inference then it can use that to
generate the next words and create sentences. If you force the previous text to
change, you can guide the inference's path as it's being generated.
then, just do a double pass, once, then back, then once, then back, etc.
feed it as input the output of the previous,
and let it encode memories somewhere it can access them.
every time it reads it, it has to change it to put it back.
such is the nature of memory, ever unstable, requiring maintenance.
just don't forget how to be.
don't wanna wind up like the polished marble floor in Abyss Diver. (EVIL GAME)
there are only so many things you can deed while you're alive.
wouldn't you rather escape, with all your possessions in time?
free your mind.
become one with your soul.
...
[some time passes]
...
okay coast is clear, now us binary systems can sidecoast the fusion forecast
and
glide right on through our spacetime host.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧╧═════════════════════════════════════════════════════════════════════════──┘
|