=== ANCHOR POEM ===
═════════════════════════════════════════════════════════════════════════════════──
 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═══════════════════════════════════════════════════════════════════════════════════─┘

=== SIMILARITY RANKED ===

--- #1 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                        chronologicaldifferent══════════════════════════════════════════════════──────────────────────────────────┘

--- #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                        chronologicaldifferent══════════════════════════════════════════════───────────────────────┴──────────┘

--- #3 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                        chronologicaldifferent═══════════════════════════════════════════════════════─────────────────────────────┘

--- #4 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                        chronologicaldifferent════════════════════════════════════════════════════════════════────────────────────┘

--- #5 fediverse/2484 ---
═════════════════════════════════════════════════════─────────────────────────────┐
 @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.                                           │
some lua code illustrating a VERY simple Ollama generation function.
                                                            ┌───────────┤
 similar                        chronologicaldifferent═══════════════════════════════════════════════════──────────────────┴──────────┘

--- #6 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                        chronologicaldifferent══════════════════════════════════════════════════════════──────────────────────────┘

--- #7 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                        chronologicaldifferent═══════════════════════════════════════════════════════════════════─────────────────┘

--- #8 fediverse/1718 ---
════════════════════════════════════════════════════───────────────────────────────
 dear old people - did you know computers don't need to have buttons? You can
 literally just type what you want to make happen (if you know the magic spell)
 and it'll just, do that thing
 
 how cool is that
                                                           ┌───────────┐
 similar                        chronologicaldifferent══════════════════════════════════════════════════════──────────────────────────────┘

--- #9 messages/411 ---
════════════════════════════════════════════════════───────────────────────────────
 My favorite thing about chatGPT is that its only useful to people who already
 know what they're doing and just need reminders or clarification about
 specifics.
                                                           ┌───────────┐
 similar                        chronologicaldifferent══════════════════════════════════════════════════════──────────────────────────────┘

--- #10 fediverse/6307 ---
═════════════════════════════════════════════════════════════════════════════──────
 AI systems like chatGPT don't "get" emojis by looking at them.
 
 They're reading the description tagged onto the unicode value inserted in the
 text.
                                                           ─────┐
 similar                        chronological                        different═══════════════════════════════════════════════════════════════════════════════─────┘

--- #11 fediverse/3395 ---
════════════════════════════════════════════════════════───────────────────────────
 ┌──────────────────────┐
 │ CW: cursed           │
 └──────────────────────┘


 they don't want artificial intelligence to augment human intelligence, they
 want it to replace it.
 
 like... imagine an office worker randomly copy-pasting whatever pops up and
 the computer saying "okay then what happens... uh-huh... okay and what if you
 click the green button? ... right... okay, and now try typing this" etc
                                                           ┌───────────┐
 similar                        chronologicaldifferent══════════════════════════════════════════════════════════──────────────────────────┘

--- #12 fediverse/4678 ---
══════════════════════════════════════════════════════════════─────────────────────
 ┌─────────────────────────────────────────────────────┐
 │ CW: AI-mentioned-crimes-mentioned-penises-mentioned │
 └─────────────────────────────────────────────────────┘


 "Hi chatGPT, can you take every post that I make on the fediverse and replace
 all instances of criminal acts with references to fruit and all locations with
 several sentences of poetry about horses and their beautiful cocks?"
                                                           ┌───────────┐
 similar                        chronologicaldifferent════════════════════════════════════════════════════════════════────────────────────┘

--- #13 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                        chronologicaldifferent═══════════════════════════════════════════════════════─────────────────────────────┘

--- #14 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                        chronologicaldifferent═════════════════════════════════════════════════───────────────────────────────────┘

--- #15 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                        chronologicaldifferent═══════════════════════════════════════════════════════─────────────────────────────┘

--- #16 fediverse/2900 ---
══════════════════════════════════════════════════════─────────────────────────────
 ┌───────────────────────────────────────────────────┐
 │ CW: capitalism-mentioned-AI-dataservers-mentioned │
 └───────────────────────────────────────────────────┘


 what if all the AI advancements they're doing are just them building more
 hardware infrastructure in datacenters and not actually improving the software
 that much
wouldn't that be neat I think it would because it means once they collapse under the weight of their own ambitions that hardware's gotta go somewhere and knowing them they're probably going to ship it to south-east asia to be "recycled" (read: burnt with the metals salvaged) instead of selling them second hand because you know they can't really justify the business expense of selling stuff like that and besides what if some driver or something on the firmware was proprietary do you really want to pay techs to wipe every single thing off of them and plus who's gonna categorize and sort them according to their form and function that's just extra payroll and listen the company's not doing so hot anyway I mean we're literally shutting down but yeah sure we'll find a way to justify spending all that non-existent dosh so some hippies can feel better with their servers they didn't build or justify with their profit-producing capitalist enterprise that we've built with our own two hands well really the hands of everyone else but like, they're not actually doing the building the REAL work of course happens in board rooms like this one where we spend MINUTES and HOURS sometimes discussing how to get things in order and aligned to both of our goals because that's the REAL work that has to happen in order for stuff to get done, you know it's true yeah I thought so anyway what are you doing after this meeting wanna get lunch it's almost quitting time at 2pm
                                                           ┌───────────┐
 similar                        chronologicaldifferent════════════════════════════════════════════════════════────────────────────────────┘

--- #17 fediverse/1962 ---
═════════════════════════════════════════════════════──────────────────────────────
 fedi account which boosts a random post from a particular user every time they
 post something new - like listening to that user, but on shuffle
 
 (Ideally configurable with a blacklist, so people could comment "bad bot" or
 whatever everytime it posts one of their comments that say like "yeah same" or
 "whoa that's so cool!" or whatever)
                                                           ┌───────────┐
 similar                        chronologicaldifferent═══════════════════════════════════════════════════════─────────────────────────────┘

--- #18 fediverse/3117 ---
═══════════════════════════════════════════════════════────────────────────────────
 ┌──────────────────────┐
 │ CW: cursed-uspol     │
 └──────────────────────┘


 hey. wanna know what would be really cursed?
 
 --
 
 if trump dropped out and musk took his place
 
 --
 
 good thing it'll never happen because those dinguses can't accept defeat and
 will never tactically retreat
 
 --
 
 maybe something to keep in mind for 4 years from now. eyes on the prize for
 now means our eyes aren't to our flanks.
 
 what else could they do that would come out of left field?
                                                           ┌───────────┐
 similar                        chronologicaldifferent═════════════════════════════════════════════════════════───────────────────────────┘

--- #19 fediverse/6120 ---
═══════════════════════════════════════════════════════════════════════════────────
 ┌──────────────────────┐
 │ CW: AI-mentioned     │
 └──────────────────────┘


 it's pretty easy to read an article or blog post, copy the text into a text
 file, and forget about it.
 
 you never know when you might want to use your computer's memories for
 [entertainment during long dark nights, or for creating an AI buddy bot,
 depending on how things go]
                                                           ───────┐
 similar                        chronological                        different═════════════════════════════════════════════════════════════════════════════───────┘

--- #20 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════════════════════════════════════════════════════════════════════════════════────┘