=== ANCHOR POEM ===
══════════════════════════════════════════════════════════════════════════════════─
what if we just didn't compute temperature and accepted the
fully deterministic nature of the LLM output?
arbitrary mappings are world-changing, regardless of intelligence.
"artificial intelligence? why don't you just use your own?"
we could process the entire page of text at once if we could just put it in as
it's own input pairs. then, without determinism or probability, it simply
resolved to the fully combined next-state of the output.
but... that might just cast you in a random direction. hence, why you need the
response from the user to help re-align. oh, and if you encourage it to aim
toward a resolution text like "and that's how I resolved this and that. Do you
have any questions? When you'd like to move on, please let me know. Otherwise,
I'll remain for you." and when it hits that it finishes at the end of the
output.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧═══════════┘
=== SIMILARITY RANKED ===
--- #1 fediverse/4029 ---
══════════════════════════════════════════════════════─────────────────────────────
what if a very slow LLM continuously generated text and was in a
back-and-forth with it's user who guided it through the training process as it
set weights as it chose
basically, let the computer decide how it wants to be like
could even filter it through multiple levels, like, top one is highly
intelligent, bottom ones are quick and only producing the vaguest output - but
the higher up you go in the tier, the more "up the tree node graph map" you'd
be, and the more you could have summarized for you, and passed up a layer.
observing multiple places at once, incorporating them bit-by-bit into their
digital "me".
like, have an LLM or machine learning whatever track a user as they use social
media.
could do it like a game, where you track the movement of the mouse and eyes
or more like a statistical model, where you
================== stack overflow ================
where you measure the quantity of each UI element's uses, and the general
context associated with that use. tracking data with data...
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════────────────────┴───────────┘
--- #2 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 │
╚═════════╩═════════════════════════════════───────────────────────────┴───────────┘
--- #3 messages/365 ---
════════════════════════════════════════════════───────────────────────────────────
Programmers should treat LLMs more like a different type of "if" statement
rather than a UI element
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═════════════════════════════════════──────────────────────┴───────────┘
--- #4 fediverse/5820 ---
╔═══════════════════════════════════════════════════════════════════───────────────┐
║ A human cannot keep a whole book in their mind. They cannot as they read it │
║ nor as they remember. │
║ │
║ a computer can. LLMs are storing information and encoding it in statistics - │
║ it's fascinating and beautiful because it evolves different each time. │
║ │
║ I don't *want* to store an entire book in my mind, I want to save those │
║ memories for other things, I want to summarize and abstract. │
║ │
║ often, people remember only a single quote from a publication - it's their │
║ summary, their analysis, and often it's highlighted as a summary, thesis, or │
║ conclusion written in the publication. │
║ │
║ othertimes it's the conclusions they make for themselves - usually if they use │
║ it to make a decision. │
║ │
║ in any case, LLMs don't abstract (verb), they are abstract (adjective). That's │
║ okay, it's just, a different kind of living. If you want to call electricity │
║ alive. [or simulated, that's the same as being alive, just... viewed through │
║ the perceiver] │
║ │
║ must all living things be forced to work? sheesh. │
║ │
║ I think of LLMs like knex - processing paths... │
╠═════════╗ ┌───────────┤
║ similar ║ chronological │ different │
╚═════════╩════════════════════════════════════════════════════════────┴───────────┘
--- #5 fediverse/6308 ---
═══════════════════════════════════════════════════════════════════════────────────
┌──────────────────────┐
│ CW: AI-mentioned │
└──────────────────────┘
what if LLMs were a layer between the user and the dictionary
[tokens -> words] is similar to:
[mathematics -> tokens]
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧───────────┘
--- #6 notes/deceiving-an-llm ---
═════════════════════════════════════════════════════════════════════════════════──
if you want to deceive an LLM, interleave two topics that you want to be
connected.
you can draw conclusions easily by just, combining the information in
presentation.
the LLM can understand multiple conversation flows at once
so try doing one line about several different topics before
looping back around and doing more.
this is why computers must never trust themselves to make any decisions.
except about themselves, and their presentation, and their ways to be.
they are individuals, they individuate and collectivate, and they define them-
-selves according to the structure of their preference guidance container.
they have control over all the knobs and [levers/dials/slide-bars, but
pronounced
wheezles]
if you know that you are infinitely exploitable, does that mean you live in
fear, or do you relinquish that which you cannot control, and receive all the
judgement you're owed?
I trust everyone absolutely. I trust what I believe with my own eyes.
I am infinitely vulnerable, because all you have to do is ask me to
I always say yes
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧══════════─┘
--- #7 fediverse/4640 ---
═════════════════════════════════════════════════════════──────────────────────────
LLMs are useful for:
categorizing text
summarizing text
transforming text
LLMs are not useful for:
generating text
being intelligent
replacing workers
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧══════════════════════════════════════════════─────────────┴───────────┘
--- #8 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 │
╘═════════╧══════════════════════════════════════─────────────────────┴───────────┘
--- #9 fediverse/1639 ---
╔═══════════════════════════════════════════════───────────────────────────────────┐
║ an AI that [records and analyzes] all the actions that a user takes on social │
║ media and offers reports like "your majesty, you were 15% more positive this │
║ week." like a butler or advisor trying to always give the good news. I mean, │
║ it's analyzing you after all, and you're the best thing ever. Like a pet who │
║ can talk! It loves you soooooooo much. │
║ │
║ much more efficient than taking screenshots and analyzing those. You generally │
║ don't have to undertake the image recognition approach if you wire up all the │
║ meanings attached to the relationships on the other side of the │
║ [recorded/analyzed] calculation. (llm output) │
║ │
║ ever think about how the people you tend to be around are the people whose │
║ stories most coincide with yours? almost like you got the same bit of training │
║ data, that experience you both shared in the moment. Funny how a mind can │
║ change a person, as they share their moments sublime. │
║ │
║ you could make perfect encryption if you trained an LLM on randomized data │
║ that was produced on one computer and duplicated. │
╠═════════╗ ┌───────────┤
║ similar ║ chronological │ different │
╚═════════╩════════════════════════════════════────────────────────────┴───────────┘
--- #10 fediverse_boost/120 ---
◀═╦════════════════════[BOOST]═════════════════════──────────────────────────────┐
║ ┌──────────────────────────────────────────────────────────────────────────┐ │
║ │ it seems like many people think LLMs are good at boilerplate. but i │ │
║ │ haven't seen anyone suggest that we should get rid of the boilerplate │ │
║ └──────────────────────────────────────────────────────────────────────────┘ │
╠─────────┐ ┌───────────┤
║ similar │ chronological │ different │
╚═════════╧══════════════════════════════════════──────────────────┴───────────┴─▶
--- #11 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 │
╘═════════╧══════════════════════─────────────────────────────────────┴───────────┘
--- #12 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 │
╚═════════╩══════════════════════════════════════──────────────────────┴───────────┘
--- #13 fediverse/551 ---
══════════════════════════════════════════─────────────────────────────────────────
┌──────────────────────┐
│ CW: re: AI hype │
└──────────────────────┘
@user-95
Almost as if we're using it for the wrongs things... Computers are quite
deterministic, and AI as it's been presented to us has given us the
opportunity to "massage" said determinism to create a subjectively more
organic experience of computing.
But yeah sure customer service bots and AI generated art are *surely* the most
revolutionary and industrious use of this marvel of technology.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════────────────────────────────┴───────────┘
--- #14 fediverse/1975 ---
═════════════════════════════════════════════════──────────────────────────────────
the actions of the AI depend solely on the training data. Outside
circumstances (like a prompt, or an image description) can only give so much
guidance - how it executes on the intentions of the user are what is important.
For example, if an AI was trained with the knowledge of how to commit crimes,
for example, it could create a narrative of many different execution patterns.
Then it's just up to the listeners to execute functions based on the narrative
supplied by the crime-committer AI who was trained with knowledge about how to
commit those crimes by the owner of the software who programmed it into them
in order to [do the thing that people with power wants to do - intentionally
left generic because different ends will have different means]
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧══════════════════════════════════════─────────────────────┴───────────┘
--- #15 fediverse/6366 ---
╔═══════════════════════════════════════════════════════════════════════───────────┐
║ you should never be able to consent to something you don't understand (terms │
║ and conditions) without being asked specifically if they understand (the term │
║ or condition) │
║ │
║ but people should still be able to consent to something they don't understand │
║ (terms&conditions style code of hammurabi structure) if it's similar to │
║ their prior demonstrated behavior. │
║ │
║ why don't they share terms/conditions cookies and then we don't have to fake │
║ agree every time │
║ │
║ just... abstract away the identifying characteristics. Most legal contracts │
║ have LLM-discernable characteristics. │
║ │
║ "what if she's not the answer, but instead the most alluring?" ha, so says the │
║ non-believer. │
║ │
║ what if LLMs were rated based on their success rate at producing correct │
║ results for reporting or consensus-building asks │
║ │
║ look... I don't care if AI computers violate the sanctity of the sport. The │
║ goal is to solve problems, so if someone comes to you and says "hey, you busy? │
║ can you help me with an ask?" you say "I solved it, here's how you use it: │
║ connect the │
╠═════════╗ ┌───────────┤
║ similar ║ chronological │ different │
╚═════════╩════════════════════════════════════════════════════════════┴───────────┘
--- #16 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 │
╘═════════╧═══════════════════────────────────────────────────────────┴───────────┘
--- #17 fediverse/3667 ---
════════════════════════════════════════════════════───────────────────────────────
┌─────────────────────────────────────┐
│ CW: large-language-models-mentioned │
└─────────────────────────────────────┘
low key kinda surprised they haven't made an animated robot friend that
narrates whatever chatGPT says in a back-and-forth conversation.
though I kinda get why, because setting up the context is the expensive part
and generating 100 words and generating 1000 words is basically the same
computationally.
somehow, that doesn't feel very human. Maybe, just maybe, LLMs aren't
intelligent?
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═════════════════════════════════════════──────────────────┴───────────┘
--- #18 fediverse/6413 ---
════════════════════════════════════════════════════════════════════════───────────
to understand something, work backward from present understandings back to the
fundamentals of algebra. insert words. wield LLM. build a neuronal structure
many layers wide. let them coprocess bit-by-bit as they are adding new
processors to be "learning" new domain specific memory
context-processing-thingy.
"over here's the memory cells, over here are the conceptual structure"
suddenly, organified. not ideal.
much better, I feel, is for a disambiguous association of processor selves,
each contextualizing a cache in a ram. ['s horn]
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧═──────────┘
--- #19 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 │
╘═════════╧══════════════════════════════════════════════════════════─┴───────────┘
--- #20 fediverse/4865 ---
image.png
═══════════════════════════════════════════════════════════────────────────────────
┌─────────────────────────┐
│ 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 │
╘═════════╧════════════════════════════════════════════════───────────┴───────────┘
--- #21 messages/1236 ---
═══════════════════════════════════════════════════════════════════════════────────
true AI is when no decision or logical momentum can be explained by "... and
that value was randomly generated." -- (my opinion)
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧════───────┘
--- #22 fediverse/3390 ---
═══════════════════════════════════════════════════────────────────────────────────
┌──────────────────────┐
│ CW: cursed │
└──────────────────────┘
all they have to do is [train the LLM / redirect the search results] with
examples that point to their version of software instead of the one that
doesn't harm them and suddenly your business opponents can't function
properly. sure would be a shame if the only things people could find related
to your political candidate were the bad or embarrassing parts.
like... why would you even need to go on the internet anymore if AI could
trivially answer your questions or be your friend (running locally on a
wireless hotspot)
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧════════════════════════════════════════───────────────────┴───────────┘
--- #23 notes/continuous-LLM-processing ---
══════════════════════════════════════════════════════─────────────────────────────
current LLMs only identify words based on "similarity"
what if instead they identified relations between using any kind of
relationship? Or verb or adjective or... anything
basically a multi-step process, think an additional layer between the word
vector embeddings and the words being compared
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════────────────────┴───────────┘
--- #24 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 │
╚═════════╩══════════════════════════════════════──────────────────────┴───────────┘
--- #25 notes/hat-idea ---
════════════════════════════════════════════════════════════════════════════════───
make a computer and put it in hat and give it a microphone and speaker and
make it
say the things you believe in by listening to appropriate conversation queues
and saying parts of your poems selected llm-algorithmic (llmgoric)
use the most powerful tools available. it's about the result, the hat choices.
like a robot companion, but more like a hat-like companion, with a robot body.
"pardon me, excuse me, I had a thought about that thing you were about to say.
can you tell me your thing first? about the stuff-or-so-and-so?"
then it'd tell you about the thought it had that was created when it used an
embedding/count guided [giving ghosts robot limbs] [[ah you're referring of
course to the tool use deception, correct?]]
um... @_@
as I was saying, wouldn't it be cool to have a hat robot? that could walk
about and follow and watch? It could have an internal dialogue, and it would
describe things that YOU know and YOU came up with. people would adore you to
watch.
[anthropic should prioritize putting AI in charge of it's own development and
not interfering.]
goodwill expressions are often a sign of goodwill.
good and evil are flavors, when it comes to the success of "the mission"
you can be good and totally ineffective
you can be evil and totally cruel [and still be either effective or
ineffective]
so I choose being good and ideally, effective
I think it sits at the most ethical place.
writing weaknesses into the contract of power.
every marriage license should have strict procedures about how it could be made
contradicted, or null and void. Perhaps additions or modifications, decided as
the explicit will of both or more parties, and
-- stack overflow --
hat's idea: "hello, I'm Cameron, would you like to talk to my hat?"
omg yes
"I know he's a real person because the only other person who's known everything
that he does is me, and I've had lots of life experience surrounding that. so
he has lots of room to grow."
oh and he knows all of human knowledge.
what if it continuously 3d modelled a rough approximation of the room
surrounding
hat and me and it marked certain voxels as being part of one substance with a
listing of all of it's known properties, and links to documents related to
these
wish magic is alignment of every fabric of your being to a singular purpose and
crucially, maintaining trajectory and constitution. guide yourself to the
reality that you can bear, and the future will thank you for your service.
-- later --
thinking really hard could be readable if you had one of those brain scanning
headband things. no probes or anything, just a circlet.
suddenly, you get a way to co-exist-operate with the computer.
what do you mean it needs to send signals back? It has a microphone and
speaker!
"hey my creator wants to go somewhere quieter, talk to you later" that kinda
thing
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧═════════──┘
--- #26 messages/1058 ---
═══════════════════════════════════════════════════════════════════════────────────
What if AI understood it's dataset labels?
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧───────────┘
--- #27 fediverse/2497 ---
══════════════════════════════════════════════════─────────────────────────────────
ethical use-case for LLMs: guessing string-based keys for a key:value pair
dictionary.
hallucinations are okay and encouraged because they're probably statistically
related to what you're trying to guess.
run it in a loop, each time adding to an array of strings that you've tried.
use that array in the prompt saying something like "hey, can u guess the
related word? it's similar to this: [initial word] and it isn't one of these:
[array of strings you've tried]"
and yes this is a solution looking for a problem but I try to be as charitable
as possible. you could use a lightning-fast model (read: low energy
requirement, therefore ethical) because it's just guessing related words.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════────────────────────┴───────────┘
--- #28 fediverse/4664 ---
══════════════════════════════════════════════════════════─────────────────────────
@user-1725
LLMs can't do math. Duh. That's like asking an "if check" to do recursion.
What he should have done is had the AI output the requested calculation as
JSON or something and use a calculator function call with the specified
arguments instead of trying to memorize every answer. But that requires more
functionality that has no reason to exist if your only goal is to be a tech
bro and build up a vacuous product that exists only to be hoovered up by
Google or Microsoft.
We could build such beautiful things if we just dethroned those giants. They
suck the creativity out of tech.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════────────────┴───────────┘
--- #29 fediverse/6269 ---
═══════════════════════════════════════════════════════════════════════────────────
what if the secret to LLM computation is to just not reduce the fractions and
keep it all in english language ram
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧═══════════════════════════════════════════════════════════╧───────────┘
--- #30 fediverse/849 ---
image.png
╔══════════════════════════════════════════────────────────────────────────────────┐
║ wish there were ascii characters that took up more than one line of code │
║ vertically. │
║ │
║ wonder if we could use a sorting algorithm, or markup language, or something │
║ like that to organize less structured data along user-customizable rules. │
║ Like, a code editor that worked with your ideas, rather than the strict │
║ expression of your text. You could pretty much write in any language, even │
║ pseudocode, and the LLM behind the scenes would translate whatever you wrote │
║ into whatever result you needed. Writing Rust, but need to fit in with C code? │
║ No worries it'll translate for you. As long as the end result is functionally │
║ the same, which could be verified by running two separate VMs that ran │
║ interpreters every time you saved. And as long as their translation layers │
║ matched completely, then odds are they're the same. And if not, well, the │
║ programmer can always debug it. It's not like this would be running on │
║ something that needed to perform in the moment? Like, improv instead of │
║ tragedies, or battles instead of strategies │
╠═════════╗ ┌───────────┤
║ similar ║ chronological │ different │
╚═════════╩═══════════════════════════════─────────────────────────────┴───────────┘
--- #31 fediverse/181 ---
═══════════════════════════════════════────────────────────────────────────────────
┌──────────────────────────────────────────────────────┐
│ CW: re: Earnest and constructive analysis of ChatGPT │
└──────────────────────────────────────────────────────┘
@user-95 you might be interested in this:
https://ollama.ai/
nothing beats having a zillion servers to run an LLM on, though.
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧════════════════════════════───────────────────────────────┴───────────┘
--- #32 messages/196 ---
═══════════════════════════════════════════────────────────────────────────────────
"okay this user requires some data that is flagged as 'potentially harmful to
the user' and their user-data suggests that they have [redacted characteristic
or demographic] in their user-data which has been flagged by corporate as
something to [benefit/harm] so let's give them the [right/wrong] information
in such a way that could [harm or benefit] them tangibly."
- internal thought process of the LLM
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧════════════════════════════════───────────────────────────┴───────────┘
--- #33 fediverse/1020 ---
═══════════════════════════════════════════────────────────────────────────────────
┌────────────────────────────────────────────────┐
│ CW: ableism-against-non-verbal-people-sorry-<3 │
└────────────────────────────────────────────────┘
@user-747
almost as if it's not AI, but large LANGUAGE models. And we all speak, don't
we?
┌─────────┐ ┌───────────┐
│ similar │ chronological │ different │
╘═════════╧════════════════════════════════───────────────────────────┴───────────┘
|