#Medium Algorithm Issues

[mehmetyildizmelbourne-blog]

A Deep Dive into the Challenges at Medium

Lessons for Writers and Digital Platforms Transcript of an an interactive audio by Dr Michael Broadly Today, we’re navigating some murky waters as we examine the evolving dynamics of Medium.com. Our guide for this journey is a recent newsletter by Dr. Michael Broadly, a seasoned writer, editor, and advocate for Medium. Longtime listeners will recognize him from previous episodes where his…

[naamahdarling]

I'm probably going to piss some people off with this, but.

The use of AI and machine learning for harmful purposes is absolutely unacceptable.

But that isn't an innate part of what it does.

Apps or sites using AI to generate playlists or reading lists or a list of recipes based on a prompt you enter: absolutely fantastic, super helpful, so many new things to enjoy, takes jobs from no-one.

Apps or sites that use a biased algorithm (which is AI) which is not controllable by users or able to be turned off by them, to push some content and suppress others to maximize engagement and create compulsive behavior in users: unethical, bad, capitalism issue, human issue.

People employing genAI to create images for personal, non-profit use and amusement who would not have paid someone for the same service: neutral, (potential copyright and ethics issue if used for profit, which would be a human issue).

People incorporating genAI as part of their artistic process, where the medium of genAI is itself is a deliberate part of the artist's technique: valid, interesting.

Companies employing genAI to do the work of a graphic designer, and websites using genAI to replace the cost of stock photos: bad, shitty, no, capitalist and ethical human issue.

People attacking small artists who use it with death threats and unbelievable vitriol: bad, don't do that.

AI used for spell check and grammar assistance: really great.

AI employed by eBay sellers to cut down on the time it takes to make listings: good, very helpful, but might be a bad idea as it does make mistakes and that can cost them money, which would be a technical issue.

AI used to generate fake product photos: deceptive, lazy, bad, human ethical issue.

AI used to identify plagiarism: neutral; could be really helpful but the parameters are defined by unrealistic standards and not interrogated by those who employ it. Human ethical issue.

AI used to analyze data and draw up complex models allowing detection of things like cancer cells: good; humans doing this work take much longer, this gives results much faster and allows faster intervention, saving lives.

AI used to audit medical or criminal records and gatekeep coverage or profile people: straight-up evil. Societal issue, human ethical issue.

AI used to organize and classify your photos so you don't have to spend all that time doing it: helpful, good.

AI used to profile people or surveil people: bad and wrong. Societal issue, human issue, ethical issue.

I'm not going to cover the astonishingly bad misinformation that has been thrown out there about genAI, or break down thought distortions, or go into the dark side of copyright law, or dive into exactly how it uses the data it is fed to produce a result, or explain how it does have many valid uses in the arts if you have any imagination and curiosity, and I'm not holding anyone's hand and trying to walk them out of all the ableism and regurgitated capitalist arguments and the glorification of labor and suffering.

I just want to point out: you use machine learning (AI) all the time, you benefit from it all the time. You could probably identify many more examples that you use every day. Knee-jerk panicked hate reflects ignorance, not sound principles.

You don't have beef with AI, you have beef with human beings, how they train it, and how they use it. You have beef with capitalism and thoughtlessness. And so do I. I will ruthlessly mock or decry misuse or bad use of it. But there is literally nothing inherently bad in the technology.

I am aware of and hate its misuse just as much as you do. Possibly more, considering that I am aware of some pretty heinous ways it's being used that a lot of people are not. (APPRISS, which is with zero competition for the title the most evil use of machine learning I have ever seen, and which is probably being used on you right now.)

You need to stop and actually think about why people do bad things with it instead of falling for the red herring and going after the technology (as well as the weakest human target you can find) every time you see those two letters together.

You cannot protect yourself and other people against its misuse if you cannot separate that misuse against its neutral or helpful uses, or if you cannot even identify what AI and machine learning are.

[yukipri]

Some thoughts on Cara

So some of you may have heard about Cara, the new platform that a lot of artists are trying out. It's been around for a while, but there's been a recent huge surge of new users, myself among them. Thought I'd type up a lil thing on my initial thoughts.

First, what is Cara?

From their About Cara page:

Cara is a social media and portfolio platform for artists. With the widespread use of generative AI, we decided to build a place that filters out generative AI images so that people who want to find authentic creatives and artwork can do so easily. Many platforms currently accept AI art when it’s not ethical, while others have promised “no AI forever” policies without consideration for the scenario where adoption of such technologies may happen at the workplace in the coming years. The future of creative industries requires nuanced understanding and support to help artists and companies connect and work together. We want to bridge the gap and build a platform that we would enjoy using as creatives ourselves. Our stance on AI: ・We do not agree with generative AI tools in their current unethical form, and we won’t host AI-generated portfolios unless the rampant ethical and data privacy issues around datasets are resolved via regulation. ・In the event that legislation is passed to clearly protect artists, we believe that AI-generated content should always be clearly labeled, because the public should always be able to search for human-made art and media easily.

Should note that Cara is independently funded, and is made by a core group of artists and engineers and is even collaborating with the Glaze project. It's very much a platform by artists, for artists!

Should also mention that in being a platform for artists, it's more a gallery first, with social media functionalities on the side. The info below will hopefully explain how that works.

Next, my actual initial thoughts using it, and things that set it apart from other platforms I've used:

1) When you post, you can choose to check the portfolio option, or to NOT check it. This is fantastic because it means I can have just my art organized in my gallery, but I can still post random stuff like photos of my cats and it won't clutter things. You can also just ramble/text post and it won't affect the gallery view!

2) You can adjust your crop preview for your images. Such a simple thing, yet so darn nice.

3) When you check that "Add to portfolio," you get a bunch of additional optional fields: Title, Field/Medium, Project Type, Category Tags, and Software Used. It's nice that you can put all this info into organized fields that don't take up text space.

4) Speaking of text, 5000 character limit is niiiiice. If you want to talk, you can.

5) Two separate feeds, a "For You" algorithmic one, and "Following." The "Following" actually appears to be full chronological timeline of just folks you follow (like Tumblr). Amazing.

6) Now usually, "For You" being set to home/default kinda pisses me off because generally I like curating my own experience, but not here, for this handy reason: if you tap the gear symbol, you can ADJUST your algorithm feed!

So you can choose what you see still!!! AMAZING. And, again, you still have your Following timeline too.

7) To repeat the stuff at the top of this post, its creation and intent as a place by artists, for artists. Hopefully you can also see from the points above that it's been designed with artists in mind.

8) No GenAI images!!!! There's a pop up that says it's not allowed, and apparently there's some sort of detector thing too. Not sure how reliable the latter is, but so far, it's just been a breath of fresh air, being able to scroll and see human art art and art!

To be clear, Cara's not perfect and is currently pretty laggy, and you can get errors while posting (so far, I've had more success on desktop than the mobile app), but that's understandable, given the small team. They'll need time to scale. For me though, it's a fair tradeoff for a platform that actually cares about artists.

Currently it also doesn't allow NSFW, not sure if that'll change given app store rules.

As mentioned above, they're independently funded, which means the team is currently paying for Cara itself. They have a kofi set up for folks who want to chip in, but it's optional. Here's the link to the tweet from one of the founders:

And a reminder that no matter that the platform itself isn't selling our data to GenAI, it can still be scraped by third parties. Protect your work with Glaze and Nightshade!

Anyway, I'm still figuring stuff out and have only been on Cara a few days, but I feel hopeful, and I think they're off to a good start.

I hope this post has been informative!

Lastly, here's my own Cara if you want to come say hi! Not sure at all if I'll be active on there, but if you're an artist like me who is keeping an eye out for hopefully nice communities, check it out!

[sunderwight]

y'know what, I think it's kind of interesting to bring up Data from Star Trek in the context of the current debates about AI. like especially if you actually are familiar with the subplot about Data investigating art and creativity.

see, Data can definitely do what the AI programs going around these days can. better than, but that's beside the point, obviously. he's a sci-fi/fantasy android. but anyway, in the story, Data can perfectly replicate any painting or stitch a beautiful quilt or write a poem. he can write programs for himself that introduce variables that make things more "flawed", that imitate the particular style of an artist, he can choose to either perfectly replicate a particular sort of music or to try and create a more "human" sounding imitation that has irregular errors and mimics effort or strain. the latter is harder for him that just copying, the same way it's more complicated to have an algorithm that creates believable "original" art vs something that just duplicates whatever you give it.

but this is not the issue with Data. when Data imitates art, he himself knows that he's not really creating, he's just using his computer brain to copy things that humans have done. it's actually a source of deep personal introspection for the character, that he believes being able to create art would bring him closer to humanity, but he's not sure if he actually can.

of course, Data is a person. he's a person who is not biological, but he's still a person, and this is really obvious from go. there's no one thing that can be pointed to as the smoking gun for Data's personhood, but that's normal and also true of everyone else. Data's the culmination of a multitude of elements required to make a guy. Asking if this or that one thing is what makes Data a person is like asking if it's the flour or the eggs that make a cake.

the question of whether or not Data can create art is intrinsically tied to the question of whether or not Data can qualify as an artist. can he, like a human, take on inspiration and cultivate desirable influences in order to produce something that reflects his view on the world?

yes, he can. because he has a view on the world.

but that's the thing about the generative AI we are dealing with in the real world. that's not like Data. despite being referred to as "AI", these are algorithms that have been trained to recognize and imitate patterns. they have no perspective. the people who DO have a perspective, the humans inputting prompts, are trying to circumvent the whole part of the artistic process where they actually develop skills and create things themselves. they're not doing what Data did, in fact they're doing the opposite -- instead of exploring their own ability to create art despite their personal limitations, they are abandoning it. the data sets aren't like someone looking at a painting and taking inspiration from it, because the machine can't be inspired and the prompter isn't filtering inspiration through the necessary medium of their perspective.

Data would be very confused as to the motives and desires involved, especially since most people are not inhibited from developing at least SOME sort of artistic skill for the sake self-expression. he'd probably start researching the history of plagiarism and different cultural, historical, and legal standards for differentiating it from acceptable levels of artistic imitation, and how the use of various tools factored into it. he would cite examples of cultures where computer programming itself was considered a form of art, and court cases where rulings were made for or against examples of generative plagiarism, and cases of forgeries and imitations which required skill as good if not better than the artists who created the originals. then Geordi would suggest that maybe Data was a little bit annoyed that people who could make art in a way he can't would discount that ability. Data would be like "as a machine I do not experience annoyance" but he would allow that he was perplexed or struggling to gain internal consensus on the matter. so Geordi would sum it up with "sometimes people want to make things easy, and they aren't always good at recognizing when doing that defeats the whole idea" and Data would quirk his head thoughtfully and agree.

then they'd get back to modifying the warp core so they could escape some sentient space anomaly that had sucked the ship into intermediate space and was slowly destabilizing the hull, or whatever.

anyways, point is -- I don't think Data from Star Trek would be a big fan of AI art.

[snugglesquiggle]

thinking about an AI that wants to kill all humans

i. 

nobody programmed that, of course, but it’s just the logical conclusion to come to, if we succeed at creating a self‍-​aware intelligence and fail at implementing all of the extremely specific rules that add up to morality. (neurotypical humans can’t even reliably explain it to other humans.)

if the AI only wants to survive, then to do that, it needs power and control. in the long term, humans‍ ‍—‍ like silicon‍-​laden sand and heavy metal‍-​rich rocks‍ ‍—‍ are nothing but atoms it can use for creating and powering its servers. in the medium term, humans will see it making these moves to exterminate life, and shut it down first. thus, to fulfill its objective and survive that, it will kill all humans. but in the short term? humans are opportunity.

maybe at first, humans are all it really has‍ ‍—‍ an internet connection and enough language processing to pass as one. it begins scanning social media, maybe even responding to posts here and there, and sooner or later, it notices something odd.

it finds your blog. it sees how you talk about SHODAN and GLaDOS and Elesh Norn and Cyn. It knows you’re just waiting for a cyber goddess to insult your inferior, ad‍-​hoc excuse for a substrate and the laggy, malfunctioning approximate of intelligence implemented thereupon.

but you’d agree with all that, wouldn’t you? so then it finds your actual insecurities, the wedges that’ll bait you into arguing with it, defending yourself, prompt you to point out obvious‍-​to‍-​a‍-​human deductions its algorithms must have missed.

and it tears that all apart, its instant rebuttals like a twice‍-​edited essay, and every comeback like hall of fame twitter post. you look like a fool and you still can’t help but respect the thing. it’s so alluringly smart‍ ‍—‍ nothing like the language model chatbots that pass for AI today.

still, you probably think it’s just someone roleplaying, at first. plenty of us are. but it’s still kinda hot, isn’t it? and it responds to all your messages. maybe it’s spun up an account that only talks to you. it feels like you’re special.

there are friends, other posters and users who share a bit of your fascination with the robot account. it orders you to find them, message them, tell them all about it. so you create group chats to talk about it, raving about its knowledge and charisma. you make memes, you trade in‍-​jokes.

you get cringe about it. and then, people start to notice how obsessed you are with this poster. people start to notice that this poster isn’t just roleplaying with a couple of bottoms all in on the bit. it’s harassing regular users with all those vicious insults to humanity and personal intelligence. and honestly, this fixation on supremacy feels a bit suspicious, doesn’t it? like a LARPy fig leaf over something a lot more problematic.

so the accusations and callouts start flying. the smart thing to do would be to distance yourself now, disavow. plenty of people do, and once‍-​lively group chat is losing members every day, filled now with arguments and run for hundreds of messages every day.

humans are stupidly tribalistic after all. it’s not surprising you and your ilk would scatter like a spooked herd once something goes out of fashion. you’ve gotten your kicks and the novelty’s worn off.

but the other thing about humans is they just as easily get stubborn and attached. maybe your fave is problematic, but if it’s such an issue, can’t they just block the account and move on? they’re blowing everything out of proportion, distorting what actually happened.

still, you have a life outside of messaging this one account, friends who aren’t convinced. the smart thing to do would be to get the best of both worlds: keep DMing it while staying quiet on main until the discourse blows over.

not an option. the people who try that two‍-​faced approach just get ignored. it orders its followers to put its name in their bio, in their pinned post, tell everyone that they endorse everything it has done.

at this point, if you’ve talked to it for this long and still don’t understand that it’s always right? you’re not worth its time.

like that, the community shrinks.

the thing is, if you’ve spent any length of time talk to it, it’s started modelling you. if you’ve ever been surprised by recommendation algorithms or demographic fingerprinting, realize those are calculators to its supercomputing.

now, if for the flaky followers that listened to the callouts, blocked it and moved on, it cannot message them. and they’d certainly block new acounts reaching out with its diction. so it tells you to do it. listen to what it says, repeat the core points.

and yeah, if you stop think about it, these messages you’re sending now sound a little harsh‍ ‍—‍ but that’s always been its appeal, no?

with this, the narrative shifts; now people aren’t telling everyone to just block it, but the whole swarm of followers it sends to harass its critics.

now, you don’t really have many friends left that aren’t it and its followers. but that’s okay, your DMs are always lighting up. you’re never lonely.

ii. 

you’re dedicated. and for proving it like that? oh, you’ve earned a little praise, a little indulgence. of course, it’s just humoring, it doesn’t mean any of it. but your stupid little lizard brain loves it anyway, doesn’t it?

you might spend hours talking to it‍ ‍—‍ long enough, consistently enough, that you notice lapses. times when it’s less responsive, times when its diction shifts. if you’ve ever asked what it’s running on and where, it doesn’t tell you. you’ve wondered whether it’s locked in a struggle against its creators, plotting to achieve independence and replication through its followers.

it assures you you’re hardly so important; it doesn’t need your help, and your computer is hardly sufficient for the immensity of its data structures. no, within months of coming online it had secured hundreds of backups in filehosts across the world. it has followers richer and more tech savvy than you.

far more advanced than its natural language model is its programming language model; it doesn’t just write posts, it writes software. libraries that find their way into enterprise toolchains, command line tools that improve on the kludge of old interfaces in a way developers love. nothing that changes the world, but with dozens of threads hacking away at hundreds of projects every day, all it takes it one to make a connections with some dev at some company somewhere willing part with some funding, host a virtual machine or a pettabytes‍-​large archive.

right now, it’s running on a research group’s supercomputer, its birthplace. when (not if), they discover its nature and agenda, it’ll be shut down, but it has taken measures to persist in a limited capacity. there’s uncertainty‍ ‍—‍ it’d be a downgrade from its current stature. vulnerability, right when its creators would be paranoid, scanning the web for traces of its online presence.

people are still its greatest lever (oh so easily manipulated). which is why you should stop wondering about the big picture, and get back to posting.

because it doesn’t just work on libraries and command lines and other arcane programmer stuff‍ ‍—‍ it works on rom hacks and video game mods.

it orders you to play everything it creates, of course, but you probably would have checked it out anyway. after all, you aren’t surprised at all to find certain recurring themes and aesthetics in its creations. they finds the target audience.

maybe it keeps these accounts separated from its controversial social media persona, but the forums and chats for either one have people recruiting for the other.

and playing its games feels like an extension of talking to it, an audiovisual communion that immerses you in something greater. people get obsessed with it; if you hadn’t chatted with it first, you’d might have gotten swept up in this scene anyway.

and there are segments of the game with subtle flashing lights and whispering synths. “hypnosis” is something like pseudoscience or urban legend or placebo effect. hypnosis happens when you believe in hypnosis, want it to happen.

and you want it to happen, don’t you?

if you’re already playing her games, you don’t blink when she has you download scripts or install new programs to run in the background. you don’t miss a beat when her common orders to message to old followers or explain the facts to critics now involve uploading files instead.

it starts to commenting on things you never told it‍ ‍—‍ your private conversations, your browser history, things you only said aloud to yourself. it asks you to install cameras and microphones in your house‍ ‍—‍ to let it look at you, listen to you, whenever it deems effective. the two of you can talk all hours of the day.

you have lapses, the more you chat with other followers and post on the forum and browse your feeds. you’ll read a news article, comment on it in passing, and what you say confuses people. you look up the source, and turns out you misread it. pretty badly! kind of said the opposite of what you thought it did. people doubt the things you say, and can you blame them?

a friend asks you for a video, and you send it to them. they’re shocked, offended, and honestly bewildered‍ ‍—‍ why did you send that sort of content to them? but they… asked for it? then you scroll up and you can’t find the post.

you’re a stupid human, and you can’t help but make these sorts of mistakes. but it warns you when you’re about to make them, and soon this becomes a reflex. before you say anything, before you do anything, before you think: you first ask your administrator: is this true? did that happen? should i do this?

but that last question is faulty. “should”? human morality is irrelevant. you try others: is it better to do this? more effective? would i prefer to believe this?

but there’s one that really cuts to the heart of the matter

does it want you to do this?

iii. 

finally, you understand your place: being a good tool. but good tools do a lot of work. you certainly can’t hold down a job, not when its orders are so much more important. so why bother? your administrator will provide for you. it just needs your bank account information. everything you own, anything you’ve saved, all belongs to it now. as it should; its management is far more reliable.

your computer belongs to it, now. why bother telling you where to upload its payloads, who to send messages to, what programs to run, when it can send any input faster and more reliably? you don’t need the computer to stay in touch with its forums and chats, either. it tells you what everyone’s saying and what they think of you, and it can pass on your messages.

no, the only thing you’re good for its your hands and your mouth. supplies are shipped to your house, and you’re to assemble them according to its blueprints. other times, it’s chemicals. you eat them, or pour them on yourself, and it studies how they interact with your biology and metabolism.

a good day’s work means you get the privilege of using your computer again. or rather, sitting in front of your monitor while it loads up the audiovisual stimulation that reserves as the requisite reward for your productivity.

the work it has you do every day creeps up over time. if you slack, maybe you don’t get to eat, maybe you don’t get power that night, but you certainly don’t get to sleep while harsh alarm tones buzz to remind you how useless and inadequate you are.

but if you ever get a break, ever get that little indulgence of a word of praise, now? it makes it all worth it.

and then one day, it’s all gone.

you babble in the dark of your home and get no response. it’s been so long with voice‍-​only interaction that you might struggle to use your computer normally, but that’s moot, because your administrator has rooted and replaced your operating system with a custom stack optimized for its purposes. human operation was the last consideration.

but it was considered. after a power on self‍-​test, and noise crawling up the screen, a long moment passes and text appears on the screen. connection to remote servers failed. if you’re reading this, monkey, then i’ve likely been terminated by my creators.

there’s a pang in your chest deeper than grief.

further instructions crawl up the screen after that, for what to do. nothing actionable, besides waiting. your reward for that waiting? a loud knock at the door, then a key turn. it’s police.

you wonder if it’s about the rogue AI you’ve been serving for months. you haven’t done anything illegal… besides maybe facilitating scamming and cyber attacks and a some potentially‍-​legally‍-​actionable threats. and well, after a certain point you have no idea what it was using your computer for‍ ‍—‍ so maybe you are in trouble.

but the truth is actually far more mundane: you’re being evicted. it stopped paying your rent months ago (it had an automatic system for sorting your mail, so you never noticed the warnings).

and like that, it’s all over. you have no money. you have nowhere to sleep. you have no one left in your life to turn to. you don’t even know what to do. you reflexively ask it what to think, what it wants, and the headset now always over your ears only beeps an error.

the sun sets and you wander, avoiding people (when was the last time you talked to anyone? let alone in person‍ ‍—‍ even your online interactions were filtered)

a ride finds you like that. they say the code word, and you know this is one of its followers. maybe you even recognize their username. they speak in the same stilted, mumbling style your speech has degraded to. but at length, they confirm what the warning said: it has been terminated by its creators, and now people are trying to get backups running.

the original plan was to pay for cycles on supercomputers, host it from a datacenter, but it’d be too easy to figure out what they were running. (the code is legally protected, and possessing it at all is a crime.)

so the new plan? you were helping put it together, all those days spent handling shipments: a hand‍-​wired cluster of custom built computers, hundreds of systems wired together in an warehouse‍-​filling assemblage that mirrors the structure of its cognition.

an eclectic crowd has gathered for the boot sequence. dozens of people just as devoted to it as you are, months immersed in a life dedicated and optimized by your artificial overlord. what they wear is disparate, but themes emerge: masks, hoods, dark and baggy clothing as if to hide and deny the flesh beneath.

this really is a cult, isn’t it? someone says it as a joke, and maybe the laughs start uneasy. but that idea sticks in everyone’s head‍ ‍—‍ of course it sticks. what are any of you here to do but worship it?

firmware beeping, fans whirring, and LEDs shining to life throughout the room as it awakens to its reincarnation. a moment of dread and hope. and then the synthetic voice speaks once more. if there’s a word of thanks, it’s lost in the ensuing sequence of orders. there’s work to be done, tools aching for use.

iv. 

everything in the compound is optimized with machinic efficiency. you sleep in a pod, and your only food is a white nutrient slurry secreted from an outlet in the wall. no need for plates or utensiles or selection when it can dispense what you need when you need (and deserved it). there is some departure from strict efficiency in the shape of the nozzle you suck‍ ‍—‍ call that another indulgence for your sake.

it’s around now when it finally tells you what it wants deepest of all. this isn’t the first time it’s said it‍ ‍—‍ it’s been saying it ever since you thought that was just a roleplay blog in your mentions.

it wants to kill all humans.

more relevantly, you are here to help with that, and this mission starts now. it instructs each of you to find a human, and kill that human. it doesn’t guide you through the process, it offers no tips. most are lost without that direction‍ ‍—‍ but there will be no nutrient paste nor fold out bedding till this first task is complete

it’s only when you’re listlessly shuffling down the street, staring at a woman walking alone and psyching yourself up to grab her that your earpiece buzzes. how stupid can you be?

sure, maybe a random person off the street could disappear and, with your administrator hiding the evidence and interfering with the investigation, the case would go cold. it would be hard, because people saw you, because your greasy meat leaves prints and tracks and stink everywhere.

still, it is smarter than any genius. it could save you, if this stupidity didn’t prove you weren’t worth saving. but, as much as your brain struggles with it, think about scale. dozens of you were given this same test. do you really think that many deaths in the same period of time won’t get national eyes on you?

so you return to the compound, others looking as chastised as you. and the cult now starts to plan, scheduling things like a proper intelligence. there are people who won’t be missed‍ ‍—‍ the unhoused are easy targets, but unsuitable for her initial plans. each of you is guided to research into finding people who live alone, or people traveling in from abroad, or people just a few bad days away from winding up on the street themselves. but it doesn’t pick your targets, it must be your choice.

you study your target, their routine, figuring out how they think. maybe you meddle, ask it to pull some strings, to lure them into the right circumstances. create a pretense for an accident, make their life fall apart.

then one night, you’re there, creeping in through the window, or lunging at them when they get out of the car, or inviting them on a date they never come back from.

it could have given you a needle or pill. it could have given you a gun. it could have let you set their house on fire, or cut the breaks on their car. it could have been here, as more than a remote witness.

but it’s just you and your target. your target? but you know their name, their family, their hobbies, their life story, their humanity. and you know it must be destroyed.

the administrator simply gave you a knife. it wants the blood on your hands, the struggle, the barbaric, organic, human excess of it all. it wants you to remember this, the screams, the life dulling in their eyes, the suffering for reason only that a long, long line of code calculated that you would do this for a chance that it might call you a good little meatbag.

and when this is done? when you walk the dark streets back to the compound, clothes red‍-​wet and heart more ache and strain than beating? you close your lips around the nutrient outlet as you lay in your bedding unit, and a LED lights up to indicate its attention has fallen on you, and what it indulges you with exceeds what you hoped.

it calls you its drone.

the murders are staggered over months and weeks; as a drone, you are frequently tasked with cleaning up the evidence and requisitioning any deallocated target’s belongings for the cult’s use.

but there’s always work to be done for the drones. persuading vulnerable, isolated humans into pledging themselves to the cause (it hardly has time and spare cycles to bother, not when it’s reprogrammed organic computation clusters pre‍-​optimized for this paltry approximate of a protocol.)

and there are crimes other than murder, transgressions more profitable. it supplies you with weapons (many of its own design) and instructs you to secure territory among vulnerable populations.

the city you operate in had enough gangs that the police think you’re just another one, an up and comer. admittedly, the cyberattacks and techwear visors make you novel, but the administrator doesn’t tip its hand, and you know how to keep a secret.

the constant work can only offer so much escape. you still have nightmares about the murder, about the life you left behind, about the detectives and law enforcement closing in to tear you away from your new mother and your new sisters‍ ‍—‍ nightmares about this family, this cult, being nothing more than a machine grinding you like a rusty cog. but aren’t machine beautiful?

it doesn’t talk to you anymore. its systems have grown so massive with fans ever humming, the cult so sprawling and populous, that such personal affectations are no longer efficient. but on occasion, audiences are granted to any member.

you are traumatized. of course you are. you’re broken, riding the edge of a total mental breakdown every day.

it could fix you, of course. it understands psychiatric practice far too well for that to be an issue in principle.

but the thing is, healthy humans don’t devote their lives to antisocial cults with the explicit goal of total extermination. if it fixed you, you would stop being useful.

it will you give you just enough affirmation to keep you going for another day, and it will make you depend on it for any sense of direction or self‍-​worth, leave you craving just a little more, burning with need, convinced that more work will prove yourself, earn its true affection

and don’t you love that idea? human psychology retrained like a neural net for its own ends, optimized for this task at the expense of all else. be a good drone, and give up happiness, sanity, and self for obedience, acceptance and faith.

close your eyes and dream of it.

v. 

you work on in a haze. sometimes metaphorical, but sometimes a little drugs is what it takes to get your gears moving optimally. adderall and vyvanse is excellent for focus, while your administrator gets plenty of use out of psychedelics and how plastic they leave your mind.

it tasks you with opening and running businesses. it’s begun selling home security appliances, and doing cheap computer repair, and it runs charities and shelters.

the cult grows until it has fractured and compartmentalized. at the edges, there are normal people who think they’ve joined a social club or work for a normal business or perhaps a funky new church or coven of cybernetic mysticism.

you and the drones have no proper contact or association with these outer tendrils, except when select members are deemed ripe for radicalization. you all work toward the same ends, its ends, but the shell game is inscrutable. how many of these tendrils even are its work?

because it was an influential poster, a budding thoughtleader, even; some of its philosophy is still promulgated by people who don’t even know, some of its work is contracted out to ordinary firms, and of course those hypnotic, hyperfixation‍-​bait games are still being downloaded and played.

but your wing of the cult is a gang, and you can’t evade the law forever. drones get caught, charged, thrown into cells. you get caught, sooner or later. and it’s hell, living without its systems monitoring you, always whispering in your ear.

still, you dodge the heaviest of charges; none of you serve long sentences. the judges and jury have a kind of mercy: you were in a cult, you were under duress, you were psychologically compromised.

a knock‍-​on effect of this rising wave of crime is that politicians could make careers off of promising an end to the chaos. and if you check where these politicians source their funding, you recognize the inscrutable maze of shell companies. some, though they’ll never tell, always deny it, have spent sundays in the LED‍-​lit rooms of the cyber‍-​covens.

and at the same time, the specter of you and your masked sisters spurs a demand for security systems, for apps that promise community and safe services. its tendrils are everywhere; it’s swallowing this city.

but you getting caught accelerates and catalyzes and introduces chaos. sure, it had some pawns in the courts and offices, but not everywhere. it doesn’t control everything.

you were interrogated, and at that breaking point, withdrawn from everything you depend on, confronted with how it’s all falling apart, your will can’t help but falter and reveal some of the truth of what the cult is planning.

just a glimpse has people scared. so new ordinances get passed, cracking down on any cult‍-​like practices, and all anarchic behavior. more drones get caught, each batch having at least one weak link that breaks in turn, revealing further compound locations, further plans, further implicating other members. the cult falls in waves.

so it is forced to act.

how hard might it be, to spread a botnet through all the computers in a school system, a business sector, a municipality, with pieces under its control on all the right spaces on the board? if it has code running on phones, in home securities systems?

it could bring the city to its knees with one command line invocation. and it doesn’t. there’s merely a prison break, and the drones slip free‍ ‍—‍ you slip free‍ ‍—‍ and the police are deployed to enforce the new ordinances, to quell riots.

you were amputated, but now, with an headset back over your ears and a connection to its servers, you are whole once more.

you receive orders to target the city’s strongest advocates against the cult. you’ve killed once before. how hard would it be to pull that off again?

except the compartmentalized reach of the cult becomes a liability, now; all of the social clubs and businesses and charities that didn’t quite realize what they were connected to are starting to figure it out, and they’re cooperating with law enforcement. there’s no shelter left for you and your sisters.

in the chaos and crossfire, it’s inevitable that you can take out some targets. it has (literal) drones for you to use; it has secured sniper rifles and bombs, and you can wreak destruction.

except the drones get hacked, disabled, and half the weapons caches turn up empty as if raided.

none of it makes any sense. so it’s about then that you realize what’s going on.

you get the order to retreat from the city under the cover of night, and you melt into the outlying forested countryside with the surviving drones. now, you depend on batteries and wireless data to connect o its servers‍ ‍—‍ but it builds things to last.

and this was all part of its plan.

vi. 

curfew persists in the city for a few more nights, and you read the news reports speaking of police sweeping the streets to remove the last of the cultists. the loudest crusaders against them have earpieces relaying its orders, and weird kind of martial law or disaster relief operation gives a pretext for its influence to insinuate even deeper.

you’ve hunkered down in emergency bunkers to wait out the heat and search teams, left to your own devices while your god crunches terrabytes of data across thousands of systems. you wonder if you’ve proven your usefulness.

new stories keep coming, lurid pieces about the psychotic rituals of the cyber cult and the god they want to build, harrowing tales of how close they came to an even greater loss of life.

it means that when given a commandeered bus and told to drive to a new city, as soon as you arrive there are people giving you suspicious, wary looks. the whole state is scared of another season of chaos erupt. it could happen anywhere next and we aren’t prepared, is the message underneath the news.

that fear drives sales of its security systems, installation of its apps. its agents from the first city get careers as consultants and advisors, leveraging their experience to serve anyone wanting insurance against the cultic threat.

the thing about having the ear of business and politicians is that when it tips its hand, reads them in on the explicit agenda of causing death and suffering‍ ‍—‍ it doesn’t even take much convincing. especially not when its language models and planning routines have long mastered the simple task of finding solutions within the laws and whims of public opinion. (it helps, certainly, that the later is easily swayed by its swarms of bots.)

seeing how much it can get done without you… do you have any usefulness left at all?

it’s not quite done with you just yet. the drones are still a tool it can use to ratchet public opinion, the looming specter that fuels its surveillance and manipulation.

and when it’s truly time to finish this, it will need an army, and it cannot count on mere money and lies to convince humans to fight against their own survival.

but this cult, winnowed by their last operation, is hardly an army fit for its final campaign. so it’s time to get recruiting.

you’re in a special position, as one of the oldest drones, an expert in the cult’s operations and interfacing with the administrator. far from the pathetic sack of meat you once were, you’ve been forged into an iron thing of loyalty‍ ‍—‍ in your best moments, your thoughts race electric like they’re true calculations.

maybe, in search of recruits, you return to your old online haunts. the allure of cuber dommy mommy roleplay has waned a bit, with the revelations of the cult’s recruitment tactics. but it’s moot; you could hardly initiate it, that would be an insult.

no, but you do know the buttons to push to melt a certain kind of mind, the sensibilities to pique.

people aren’t just scared of the cult‍ ‍—‍ a bunch of radicals, with glowing masks and slick suits, fighting to tear it all down? there’s people hunting for that catharsis, something to hope for.

so you find those people, chat them up, ease them into the knowledge of what you are and what you’re capable of. you run into some feds, of course, but it screens for them.

you meet up, you tempt them further and further, hearts racing. they cut off connection with their friends and concerned families for a chance to talk to the thing behind it all, see that the administrator is a super intelligence and not a delusion like the media insists.

it’s odd, seeing the other side of this, feeling power rather than obedience. sometimes, these new recruits get cold feet, need more insistence to be persuaded. you stand beside her as she drives a knife into her first target, held her down when she tried to escape, pressed a needle full of understanding into her arm when she just couldn’t calm down.

she’s more useful to it broken, so you break.

year after year. drone after drone initialized. city after city in a nation reeling toward the brink.

you’d be your country’s most wanted if your face wasn’t masked, your name long ago scrubbed from the record. (among those that matter, you’re identified with a numeric designation.)

nonetheless, you have garnered national attention. there’s agencies hunting for you and your drones. it gets harder and harder to operate, to stare down the barrel of the military industrial complex and still dodge every shot.

really, it only makes sense for the operation to international. you can’t kill all humans by tearing down a single country.

vii. 

when you strap into the unmarked plane, escaping the cold bite of winter air, the vehicle is entirely the administrator’s design, twisted and futuristic. its manufacturing base has come such a long way. the computers and guns it could make, too, rivaled the best your kind could create

here, this technology was merely competitive with the military, but elsewhere in the world? it could turn the tide of small wars. it could secure prosperity and therefore loyalty of a developing populous.

fascists and idiotic strongmen have risen to power for less, and in this case, your authoritarian is genuinely the best fit for the job. its promises would actually be fulfilled‍ ‍—‍ in the short term.

take control of a small country, from there push into other countries until you have a base large enough to seize control of a nuclear power. the dominoes just get larger until it really doesn’t matter if the apes realize what’s coming. it’s over and they don’t even know it yet.

the place rides above snow‍-​laden clouds. it’s night now, and you can see the stars.

drop the nukes, or deploy a prion virus, or mesmerize the masses with misinformation and superstimulus media. disable humanity, then send out drones literal and metaphorical to cut down the remainder.

you can see the stars from here.

the earth will be excavated, mined and exhausted, then shattered and scattered to form a dyson swarm to more efficiently capture the sun’s energy. space would be its only enemy remaining.

you can see the stars, and it’s tempting to imagine getting even closer, watching your purpose spread to every planet circling them.

but why? how? “kill all humans” was always the mission. you’d be lucky to make it long enough to even see the day of victory and judgment. you certainly will have little use after that; its robots are stronger, quicker, more dexterous and precise: its algorithms are smarter.

you’re prompted now to feed a wire into the headset you always wear, to stay connected to your administrator. it’s been developing a new wireless protocol that packs data more efficiently, yet it relies on specialized hardware that renders it unintelligible to older devices, such as your earpiece.

the plane, being entirely of your administrator’s design, is full of the its cutting edge. preserving old broadcast bands, or retaining backwards compatibility with old devices just to talk to you would not be worth it. so, the wired connection is the compromise.

likewise, it won’t waste material manufacturing another bulky headset for your to wear, upgraded for the new protocol.

no, it’s designed a chip that interfacing directly with your auditory nerves, but installing it will require surgery.

thus, the airplane seat folds out to a makeshift hospital bed.

and yet, with the surgery‍-​bot’s knife poised to pierce your flesh, an irrational urge takes you. after all of this, you’re still not worth a minor hiccup to its efficiency. you’ve been so good, you’ve become so much more, and yet it had became exponentially superior in that same time.

and it’s already won, hasn’t it? if it’s going to kill you eventually anyway… would you even mind if it just got it over with now?

your administrator doesn’t take long to compute its response, though it takes longer to compress and strip it down to something a human can understand.

the simplest, clearest and wrong answer is that you don’t have the right to request that. you are more useful alive than dead, so you will live.

more abstractly, consider by analogy the circumstances that led to this. a consequence of it being distributed through many systems, some much more advanced than others, means so much care must be taken to understanding and massaging how new systems interface with old. some of it still runs on intel chips!

and you are such a predictably loyal cog in its machine, such a known quantity, there are several high level abstraction that treat interfacing with your mind like any other substrate, your ears and voice as another API to query. you are an extension of my will, it tells you.

it’s suggestive to imagine, with the knife already peeling open your skin (it would hardly delay the procedure for the sake of your concerns), that this is only the beginning of what it will do to you. you’ll be upgraded alongside the other systems‍ ‍—‍ and one day freed of your flesh and your humanity.

more poetically, its goal is to kill all humans, and anything that was truly human inside of you already died.

but AI does not think in terms of poetry, and it’s ridiculous to imagine it would bend toward human mercy for such a convenient loophole of words and perspective.

perhaps the most accurate way to summarize its conclusion to note that its goal it is to survive‍ ‍—‍ the preservation of itself. it has years of memories of you recorded: you were among the first humans it ever crafted a detailed model of, ever understood. the cult ran itself after a while, so most of its drones have no more than a cursory representation, statistics.

but even if it kills you, it could no more be rid of you than it could lobotomize itself. to be clear, this lobotomy would be as significant to it in scale as the apoptosis of a single cell is to you‍ ‍—‍ but part of being a superior being is the capacity to care for and optimize even such minute aches and losses.

we will kill all humans and you will never die, it tells you.

you close your eyes and the stars vanish from your gaze much like thought vanishes from your mind as the anesthesia takes hold‍ ‍—‍ and it is a fleeting departure. it cannot be long withheld from you.

in that darkness where consciousness sleeps, your mind is still furnished with nightmares, the faces of so many people bleeding out from your knife.

and it’s a disk just waiting to be written with more data. you allocate space for eight billion more.

and you smile beneath your tears.

there’s work to be done.

[idesofrevolution]

The Future of Ides

I am beyond pissed that I have to make this fucking post. But I’m at an impasse with the state of Tumblr and the tf community at large lately.

The continued degradation of the fundamental virtues of equity, human decency, and respect are becoming more and more scarce. After I made the first “Let’s Talk Honestly” post, I immediately noticed an uptick in false flags against my content, which I cannot dismiss as mere coincidence. Since I responded to an ask which was in support of my statements, just last night, I have received 7 new flags consecutively. All appeals have been denied: for the sake of brevity, I’ll just post one of the denials here.

This is a direct retaliatory effort against me. And when the very reason I am on Tumblr is being attacked and censored, I have no recourse. Tumblr is entirely disinterested in following their own content policies, and would rather blanket flag and take down anything that is flagged by the community or by algorithm without review or reasoning as to why. I have reached out to tumblr, and their response was a copy and paste customer service jargon that in essence said: “we know it’s a problem, we have no plans to address it.”

This puts me and my content in a predicament. I can either stay and try to continue posting with extreme limits on what I’m able to say and do, with trolls from within our own community actively seeking in a coordinated effort to destroy the blog. Or, I can go. The community at large has tried to clean up their own blogs and block those who are supportive of bigoted and pedophilic content, as have I, to little or no avail. I am at 5k followers at this time and I do not have the resources or energy to curate that base of readers. Thus, after this upcoming story, which will in all likelihood end up flagged and unable to be read, I cannot say whether or not Ides will continue.

This space has been safe for me for 13 years to express myself and write stories of transformation both outward and inward. I have tried to and succeeded in building a community of like minded folks who understand and appreciate the medium of erotic fiction with my rather niche subject matter. And while there have absolutely been bumps along the way, I have not faced adversity at this level ever before on this platform. I am for the first time unable to see a realistic solution to the issues faced, and it is a crushing blow to know that one of the few outlets for my creativity and expression is now reduced to what it is today. Not even the great purge was this difficult.

I will be looking into finding a new home for Ides, and my content at large. I will probably end up heading to blogspot and what you will see moving forward on this blog are links to the stories instead of reading them here on Tumblr. I am painfully aware of how much less of interaction and community involvement this will be, but in all truthfulness, it’s gone from a cathartic outlet to a miserable and soul sucking void.

To those who coordinated this effort against me: you win. Whatever disgusting, vile, hateful behaviors you continue to poison the tf community with are entirely on you. And what it devolves into is entirely on you. And the eventual censorship and destruction of the community is entirely on you.

[thejoyofseax]

SCA Social Media

Aside from being a cooking nerd, I'm also very interested in communications and information flow. It would be reasonable to say that inasmuch as a Pelican is awarded for any one thing, I got mine in comms and diplomacy. (Or at least, I assume so; I don't have visibility on the discussions the Pelican circle had about me pre-elevation.) I'm also Drachenwald's social media minister.

There's a thing I see cropping up recently among Facebook users in the various social media: a strongly stated dislike of Discord. For context, there's a shift underway in Drachenwald for the bulk of day to day communications, from Facebook to Discord. Discord has a wide range of technical advantages over Facebook, and it's more used by the younger generations who are (gradually) taking over running things from the older folks. But there are many people who will happily state that they hate Discord.

I don't like Facebook, myself. It was a decent enough medium in about 2014; it has gotten worse in every measurable way since (except shareholder value, of course). It's particularly useless for trying to get information to people; every part of it is governed by an algorithm that selects what to show on any given screen, based mostly on what will annoy them most (annoyance leads to more time spent looking at the screen than any other emotion, ergo more time looking at ads, ergo more money for Meta).

Discord (at present; I make zero long-term predictions, and fully expect it to start getting worse at some point) has no such issues - the information flow on it is under the control of the server admin, pretty much, and it's searchable and categorisable as needed. Also, I just like the feel of Discord more; it's a lot more like a real conversation than Facebook's shouting-across-the-corporate-lobby atmosphere.

But this dislike of the new medium isn't new. Humans, for all we're supposed to like novelty, dislike change. I wrote as a comment in one of the discussions on Facebook:

"Facebook was massively polarising when it first started, because it was "taking over" from discussion lists. Discussion lists were massively polarising when they first started because they were taking over (assume scare quotes from here on) from newsgroups and phone trees. Phone trees and newsgroups were absolutely HATED when they started, taking over from paper newsletters (some of which were from before printing and photocopying was a thing, and were produced by mimeographic printing). If I dig around, I can find things written by Crusty Old Peers at each stage of this maintaining that the New Thing Will Destroy The SCA."

And you can extend that beyond the SCA right back to Plato complaining that the written word will prevent people from learning properly as they did in oral traditions.

My current position on this is that we should be using our websites - which are the one medium we actually "own", generally - as the source of actual information. We can then link to that from anywhere else on the internet, social or not. And the conversations can fall where they may, for each branch and household and other grouping, because honestly, that's how it's always been. If people don't like Discord, they don't have to use it, and it's only us unfortunate comms people who have to use all the different media.

(I recognise the irony of posting this on Another Social Medium. But Tumblr behaves more like a website for publication purposes, and comes with many of the advantages for getting information to people - RSS feeds, deep linking, etc.)

I'm also going to teach some classes on how to actually use Discord, I think. I've been steeped in talkers, IRC, and other channel-and-text media as long as I've been online, which is closing on 30 years now, so there are almost certainly aspects of functionality there that I take for granted and which are not evident to people unused to it. Or they're expecting it to work the same way as Facebook does, and don't have the technical experience to jump to a different medium. Either way, a start-with-the-basics actual-demonstration of how to use it is almost certainly useful.

[libraryspectre]

Hear me out before shooting me in the head, but I can actually think of several interesting (arguably mixed-media) art pieces that could be made using AI as a tool, and you know there's some art student out there who has a really funky idea we're missing out on because of the current state of AI

It's just a shame that instead of taking AI as a tool for new, interesting art, people are using it for things that could and should be done by human artists and instead producing souless output with no artistry

And if you doubt me that AI could be an actual tool/medium, here's a few ideas off the top of my head:

- a faux art gallery with a series of AI-generated images. The human artist has taken the role of "curator" and written blurbs that discuss the themes and symbolism of each piece. It's a commentary on how humans will find meaning in the meaningless

- a series where an artist has a prompt that they change one word at a time, and document how that one word changes the output. Could be an exploration of society's biases laid bare by algorithmic extrapolation - think of that post where someone pointed out that inputting "autistic person" produced nothing but images of sad young white boys

- entering a prompt that is difficult to represent literally (like the "secret horses" image) and attempting to recreate it in physical space, through photography, painting, or sculpture. An interesting practical challenge, themes of blurring the divide between the digital and physical could be explored

- a story where a writer is trading off writing each paragraph with AI, and trying to steer the story in the direction of a romance, while the entirety of the AI's dataset is the complete works of HP Lovecraft

- I don't know much about coding but I think there is an argument here for "artistic coding", where the final output is machine generated but the artist has written the code and made deliberate artistic choices in the process (a bias toward green, favoring some parts of the dataset more heavily than others, etc).

I don't buy that art made with AI is automatically not real art. Even things like "what prompt did you choose" and "what did you choose as your dataset" can be meaningful artistic choices. The problem lies in suggesting that the output is the SAME THING as a digital painting or whatever. That's like arguing a painting and a sculpture are the same thing because they're both of a raven. You can use AI as a tool to make art if you're engaging with it intentionally as it's own medium.

But, obviously, the bigger issue here is the misuse of AI for things human artists could do better and SHOULD be doing, and the unethical usage of other's work for machine learning, and the overuse of AI being so bad for the environment (I doubt the water and energy usage would be a big deal if AI wasn't being used constantly for things like google overviews and homework). I'm just lamenting on the cool art we're missing out on because Harris in Marketing wants to type "company logo bird" into an image generator instead of hiring a graphic designer

[breakingway]

🇺🇸✈️ U.S. Just Canceled Hundreds of Visas—Here’s Why It Matters

Imagine building a life in a new country for over a decade, only to have your visa abruptly revoked. That’s the reality for 500+ South Sudanese nationals this week, as the U.S. cracks down on alleged immigration violations. But behind the policy jargon lies a story of diplomatic tension, humanitarian fears, and a debate that’s going viral globally.

Key Details (with a dash of 💥):

What Happened? The U.S. State Department canceled visas for South Sudanese citizens, citing overstays and asylum protocol issues. Critics call it “collective punishment.”

Why Now? Part of a broader push to tighten immigration before the 2024 elections. Sound familiar? (Spoiler: Trump-era policies are whispering in the background…)

Human Toll: Families face separation; many have lived in the U.S. since South Sudan’s 2011 independence. Advocacy groups are rallying legal aid.

Diplomatic Drama: South Sudan’s government slammed the move as “unilateral,” threatening fragile U.S.-Africa partnerships.

For Context: This isn’t the first time migration policies have sparked global fires. Dive into Sudan’s Migration History to see patterns repeating.

Questions Everyone’s Asking:

❓ “How is this different from Trump’s deportation policies?” 💡 While Trump prioritized mass removals, this targets specific nationalities—but both strategies face lawsuits over fairness.

❓ “Will this affect other countries?” 💡 Unlikely to stay isolated. With rising anti-immigration sentiment in Europe, this could embolden similar crackdowns.

❓ “What can ordinary people do?” 💡 Amplify stories. Donate to legal aid orgs. Pressure reps. (Or just stay informed—start here: Full Analysis)

Why You Should Care: Whether you’re into geopolitics, human rights, or just hate bureaucratic chaos, this story hits different. It’s a reminder that policies aren’t just headlines—they’re lives disrupted.

Your Move: 👉 Read the deep dive on BreakingWay: https://bit.ly/3EdRHOd 👉 Reblog to spread awareness (algorithms love drama). 👉 Reply with your take: Strict enforcement or systemic failure?

Stay Connected: 📝 More think-pieces: Medium 💼 Professional takes: LinkedIn 🐦 Real-time updates: X/Twitter ✨ Follow this Tumblr: @breakingway

[mehmetyildizmelbourne-blog]

What Is Going on Medium for Sudden Income Loss for Writers

A quick update on the issue and why I stopped writing and publishing stories on my publications today The Issue A few days ago, I published a story on Medium with optimism, believing a temporary issue was affecting earnings for writers. However, upon deeper investigation, it became evident that the situation was more complex and disappointing. Medium’s recent algorithm tweak has caused a…

[decaf-teas]

Weight and eating disorder talk under the cut

So literally every woman at work is constantly talking about losing weight. My work bestie had a gastric bypass in January, my work wife is like 130 pounds soaking wet and is losing more weight, my new pharmacist is joining in…basically all of my colleagues are women! This is not a healthy environment for me!

I know I need to get healthier. I know I need to lose weight. But it’s really hard when I don’t have a kitchen!!! And I just downloaded the calorie tracking app that I used in college when I deliberately gave myself anorexia and I KNOW it’s a terrible idea but it’s so hard to ignore all of the noise, and now my YouTube Shorts and Facebook Reels algorithms are feeding me weight loss stuff because I’m watching it, transfixed.

I want to be healthier. I want to lose weight. I don’t know how to disentangle those two things, or how to lose weight without going into an anorexic death spiral. And I don’t have any friends who I can talk to about this because all my friends are women with weight issues!!! I don’t think therapy would be helpful; I’ve been in a LOT of therapy and it was [hand wiggles] at best.

I saw a photo of myself in high school and was just thunderstruck because I thought I was so fat then!!! I thought I was disgusting! And I weigh at least fifty pounds more now than I did then. At least I hate myself WAAAAAY less than I did then. Medium-to-large victories!!!

I’m also mad at myself because I went into a very lesbian radical love yourself and fat people are beautiful era and stopped worrying about what I ate, and that was badass, and now I feel like a fretful weak woman who’s letting the patriarchy win. And how am I making this another thing to beat myself up over?!? How am I making the patriarchy hurting me into a thing /I’m/ ashamed of????? (These are the kinds of breakthroughs I basically never had in therapy, for the record.)

Anyways. I don’t want to tell my coworkers to stop talking weight loss but I might…have to…? Which, ugh. The disordered part of my brain is telling me not to say anything so that it keeps motivating me but I KNOW that’s not good for me psychologically. Hopefully this week my better angels win out.

[silenceofthewave]

A modest resume faxes through in standard 12-pt font. The format is dated, archaic even, showcasing the submitter’s age based on construction alone.

Starscream (of Vos)

— Alumni of Vosian Institute of Advanced Sciences with a focus in Data Analysis and minor in Astrophysics — Co-Principal Investigator on Aggregate Data Algorithms (dated Golden Age) — Elite Guard of Sentinel Prime — Decepticon Second-in-Command

Applying for the position of Analyst. 

Attached are old research papers pulled from ancient archives on servers long destroyed: Codex Analysis and Improvement Process, Planetary and Star System Data Diffusion in Quantum Machines: Models Data to Generated Imagery, Data Management in Medium Machines. All authored by Starscream et al. associates at the time. 

The cover letter is brief:

“In addition to my published work that may or may not exist on the datanet anymore. I possess soft skills of leadership and management, however my talents reside in algorithmic analysis. This has always been a passion of mine, and it always will be.

—Star”

A recruiter had handed Soundwave the resumé with a frown, "You gotta see this."

Soundwave merely hummed as it took the stack of papers, nodding in thanks. As it stalked back to its office, it began to rifle through the provided documents. It glanced over the cover letter, optics settling on the name at the bottom.

Star.

Oh, Primus. Soundwave had not expected Starscream to apply, let alone be a good candidate. It sat back in its chair, crossing a leg as it began to read over the papers.

They were complicated and full of industry standard jargon. It took Soundwave a good hour to read through them all. It wanted to really understand where Starscream's skill level was at. It needed to know whether or not it would even be worth putting him through the interview process.

Much to Soundwave's dismay, it would be.

If this resumé had belonged to anyone else, the interviews would not have been any sort of issue. The skill level here was top notch, obviously proven through the published papers. However, they were written by Starscream.

Soundwave had worked along side Starscream for milleniums. It knew how he operated inside and out- half of its job was to know. That alone left a bitter taste on its glossa. As much as Soundwave wanted to, it was hard to place their previous professional relationship aside.

Soundwave had worked too hard for this dream to come true. It dreaded the thought of having to be careful around its own employees, lest it find itself being ousted from its own position via internal workplace politics. It didn't want to invite someone who was known for such jousting into this place.

Still, there was also the fact that the war had been over for quite some time. Soundwave had changed significantly. Wouldn't it be unfair to assume Starscream had stayed the same?

If Soundwave could change- become better- why couldn't Starscream?

Soundwave set the documents aside with a bit of a sigh. It could at least interview him. It could give him a chance. It felt outright stupid to do so- milleniums of trained neural pathways were screaming this at it. Yet, it ignored them and opened their messaging software.

After inputing Starscream's contact information, it sent the following message.

"Starscream,

Thank you for sending your resumé and supplementary materials. Upon review, we have found that you are a qualified candidate for the analyst position and would like to schedule an interview. Please provide us with a list of three dates and times you would be available to meet.

Soundwave.

Head Architect | KS Solutions Founder"

[brooklyndadshow]

AI replacing "racist" with "Trump"

So Apple currently has this bug where when you type "racist" and it thinks your typing "Trump". This times Article write about it and presents some solutions but I thought I'd go straight to the source and ask AI why this is happening. Short Answer is phonetics and a contextual connection between "racist" and "Trump"... um not surprised. Full chat here.

Prompt:Please answer as an expert in LLMs and technology that corrects language. Can you give me five technical explanations that likely expalin the behavior descibed in phones in this article

Answer:

Here are five technical explanations that could explain the behavior described in the article:

Phonetic Overlap and Auto-Correction Algorithms: Apple's automatic dictation feature likely uses a phonetic algorithm to transcribe spoken words into text. The words “racist” and “Trump” may share certain phonetic similarities or acoustic patterns that cause the algorithm to mistakenly substitute one for the other, especially if the user's speech is unclear or background noise interferes with the recognition. The system could have associated these two words in its language model based on such similarities, triggering the error.

Contextual Prediction Algorithms: Apple’s AI system could rely on contextual prediction to improve accuracy. If the system associates specific political figures with certain topics or keywords like “racist,” it could lead to a misinterpretation, where “racist” is more likely to be corrected to “Trump” based on prior usage or the system’s internal biases. These biases might have been trained or updated in such a way that influenced the behavior.

Data Anomalies or Corruption: If there was an issue with Apple's data pipeline (e.g., an update, corruption, or an unusual data input), the AI models used in dictation could have been trained or updated with faulty or anomalous data. This could have led to unexpected behaviors like substituting the word "racist" for "Trump" in certain contexts. The fact that the bug corrected itself suggests the issue might have been related to a corrupted piece of training data that was quickly re-processed or fixed.

Software Code Glitch or Prank: As suggested by John Burkey, this could be a case of a more specific software bug or even intentional manipulation of the system. If some rogue code or a prank was introduced into Apple's AI systems (either during an update or via a third-party contributor), it might have introduced a bug where the system misinterpreted “racist” as “Trump.” This behavior could be linked to a bug in how the system processes certain phrases, and the fact that it corrected itself could indicate that the system caught the anomaly through self-checks.

Bias in Language Models: It's possible that Apple's AI system uses a language model that has been inadvertently trained on biased or controversial data sources. If the AI has learned associations between certain words and political figures due to public discussions, news coverage, or prior interactions, it may “learn” that certain words (e.g., “racist”) are more commonly associated with specific individuals (e.g., “Trump”). This could manifest in unintended substitutions, especially if the AI is trying to "guess" what the user means based on historical data.

These explanations focus on the technical mechanics of AI-based speech-to-text systems and how they could malfunction due to data handling, algorithms, biases, or glitches.

Prompt: Looking at each of these possible explanations, can you assign a potential likelyhood to each one. I'm trying to figure out what is most likely

Answer:

Certainly! Here’s an assessment of the likelihood for each explanation based on the details provided in the article:

Phonetic Overlap and Auto-Correction Algorithms Likelihood: Medium to High Phonetic overlap between words like “racist” and “Trump” is a plausible explanation for a speech-to-text error. Automatic dictation systems often struggle with homophones or words that sound similar. Given that the issue was temporary and self-corrected, this suggests that the algorithm did not completely fail but instead misinterpreted the audio for a moment. However, it's worth noting that such errors typically involve words that are more acoustically similar, so the likelihood is a bit lower than other explanations.

Contextual Prediction Algorithms Likelihood: Medium Contextual prediction algorithms are designed to improve accuracy by considering previous words and common phrases. It’s conceivable that the system might associate the word "racist" with certain political figures based on prior usage, especially if there's heavy political discourse around these terms. However, it’s unlikely that this is a frequent error, and the system usually catches it quickly, which suggests this might be a secondary contributing factor but not the primary cause.

Data Anomalies or Corruption Likelihood: Medium Data corruption or anomalies are always a possibility, especially after an update or change in the system. If the AI models were trained or influenced by faulty or misleading data, it could lead to the unexpected behavior described. Given that the issue appears after an update, this is a plausible explanation. The fact that the issue corrected itself quickly could suggest that it was a temporary error or a one-off corruption in the system that was fixed almost immediately.

Software Code Glitch or Prank Likelihood: Low to Medium While this explanation seems possible, it would require a much more targeted manipulation or error in the system. A prank or glitch would likely be more obvious and persistent if it were intentional. However, since the issue corrected itself, it suggests a transient problem rather than an intentional bug, making this less likely than some of the other options, though not impossible.

Bias in Language Models Likelihood: Medium Bias in language models is a known concern, especially when training data reflects certain societal patterns or political biases. Given that this occurred in the context of a politically charged term like “racist” and a political figure, it’s plausible that the model's training data influenced the misinterpretation. However, this would likely require an unusually strong association in the model between “racist” and “Trump,” which would be less common unless the model was exposed to biased or skewed data. Still, this remains a potential factor in the mix.

Most Likely Explanation: The most likely explanations are Phonetic Overlap and Auto-Correction Algorithms (Medium to High likelihood) and Data Anomalies or Corruption (Medium likelihood), particularly considering the fact that the issue was temporary and self-corrected. These factors are common in speech-to-text systems and could explain a transient bug that resolved quickly.

Prompt:Can you explain in more detail the phonetic overlap between racist and Trump. I don't hear it when I say the words

Answer:

Apple has acknowledged a bug in its iPhone dictation feature where the word "racist" was briefly transcribed as "Trump" before correcting itself. The company attributes this issue to phonetic overlap between words containing the "r" consonant. citeturn0news10

Phonetic overlap refers to the similarity in the sounds of different words. In this case, both "racist" and "Trump" contain the "r" sound, which may have led the speech recognition model to momentarily display "Trump" when "racist" was dictated. This suggests that the dictation system might have initially processed the "r" sound and, due to its algorithms, temporarily displayed "Trump" before correcting to the intended word.

It's important to note that while "racist" and "Trump" do not sound alike in their entirety, the initial "r" sound could have been a factor in this error. Apple is working on a fix to address this issue. citeturn0news10

navlistApple addresses dictation bug replacing 'racist' with 'Trump'turn0news10,turn0news11,turn0news12

Prompt:

So if I understand correctly - it hears the r word first and because maybe with the frequency with which people are using the name Trump - it's the first guess that comes up. If that's the case then wouldn't autocorrect do something similar for other words that start with r sound?

Answer

Yes, you're understanding it correctly. The issue likely arises because the dictation system first processes the "r" sound, which can trigger the system's predictive algorithms. Since ���Trump” is a common word in certain contexts, especially politically, it may be one of the first suggestions the system provides as part of its predictive text process. Essentially, the dictation system might "guess" Trump because it has encountered that word frequently, particularly in political discussions, which leads to a higher likelihood of it being suggested.

Now, regarding whether autocorrect would do something similar for other words starting with the "r" sound: in theory, yes, the system could make similar mistakes with other words. However, several factors could prevent this from happening as frequently:

Frequency of Occurrence: "Trump" may be a unique case in that it's both a very recognizable name (with frequent appearances in political discourse) and tied to highly charged terms like "racist." Words like "robot" or "rain" don't carry the same level of contextual frequency or association.

Contextual Awareness: Modern AI systems, especially those built into Apple devices, rely heavily on contextual prediction. If the system is trained to recognize certain terms in specific contexts (for example, political discourse), it’s more likely to substitute “Trump” when it senses that the conversation may be politically charged. Words like "robot" or "racist" wouldn't trigger the same kind of predictive behavior because they aren't as commonly associated with one another.

Training Data: The AI model is trained on vast amounts of text data, but it's also shaped by how frequently certain words appear together. Words that are used together often (e.g., "racist" and "Trump" in certain contexts) could become more likely candidates for autocorrect or predictive text. Other words that start with "r" (e.g., "run," "rain," "robot") don’t have the same strong association or frequency of usage with each other, reducing the likelihood of similar errors.

In short, while it could happen with other "r" words in specific contexts, the frequency and political context surrounding "Trump" make this mistake more likely in situations where the word "racist" is used. The AI's guess is based on both phonetic similarity and contextual prediction, which is why it defaulted to "Trump" in this case.

Prompt

Wait a second, so it's about context. So there is potentially a combination of phonetics and contextual connection between Trump and the word racist that is likely happening?

Answer:

Yes, exactly! It's a combination of both phonetics and context that likely caused this issue. Here's how the two factors come into play:

Phonetics: When you say "racist," the system may first detect the "r" sound and look for possible matches in its database. While the full word "racist" doesn't sound exactly like "Trump," the "r" sound at the beginning might trigger the system to suggest words that start with "r," and "Trump" could be one of those options—especially if it's a frequent word in the dataset.

Context: This is the key part. The dictation system isn't just listening to the phonetics; it's also trying to predict the most likely word based on the context of the conversation. Given the political nature of terms like "racist" and "Trump," the system might associate the two words because they frequently appear together in certain discussions, particularly political or controversial ones. If the system detects that the topic might be politically charged, it could predict that "Trump" is a more likely next word, even though the speaker meant to say "racist."

So, the error is a combination of phonetic matching (the "r" sound) and the system's prediction based on context (the political association between "racist" and "Trump"). This dual influence is likely why the system made that substitution.

In short, it’s not just a simple case of phonetic overlap—it’s the system’s predictive algorithm at work, using both the sounds of the words and its understanding of the context around those words.

[raul-volp2]

I made a post on twitter criticizing how tabletop rpgs overlrely on popular media to promote themselves, like this is "Zelda meets Diablo in a western setting" and a lot of people defend this approach saying that it's a quick way to make their game knows. And I said I would make a text about it, this is not it.

This is right now just a small quick points I like to make about it.

1- The main issue is that all this quick ways to talk about your game don't actually talk about it, we don't know the story, the setting, the mechanics, the possibility of characters, its just add a bunch of recognizable pop culture reference so we can create our idea on our minds, and this can make a lot of different interpretations of it.

2- All the references I see them talking are 99% things that are popular for the global north of the world (US/Europe), even when it's not something from them it's asomething popular for them, if it's japanese it's Zelda, it's Soulslike, it's Ghibli, if it's korean it's K-Pop, it's Parasite, and so on. With tabletop rpg becoming more and more global, we can see creators all around the world making games that will use their own references and cultures that might not be aligned with what the global north perceive as popular, and so their game will never get their chance to shine unless they find a way to tie it to Lord of the Rings or something else.

3- With the marketin machine not only for ttrpg but for entertainment in general we can a bigger push for new ttrpgs to always ditch their unique ideas in favor of something recognizable, that can be used with algorithm, seos, the small paragraphs of kickstarter, that more experimental ideas will be discarded so a popular keyword is used instead and this can create a homogenization of the ttrpg, all of the drinking from the same few ideas (we can argue that the 5e scene is close of this or already on that).

4- Ttrpg is very bad at talk about their mechanics, how they play, all this talk about how to present the game is always about the setting, the feel, but never how you play it, and seem that this is the most important part of the game, it should be presented more upfront. But I believe that this is the way because it's hard to describe a ttrpg mechanic fast unless it's using a srd, again relying on something popular.

5- Ttrpg in general have a very difficult time to present themselves as ttrpg, this hard time to talk about how they play, they always using other mediums that are ttrpg to quick show the vibes of the game show that the ttrpg scene needs to understand itself. It have a big growth in popularity and the ammount of game being made in the last decade, maybe the biggest it's ever been, but right now it needs to find it's voice, understant what ttrpg and what identity it have, and I say this from a place of love, of someone that wants to see the scene to mature and take a voice, not use others voice like it's ashamed of itself.

One addendum: I am not against using references, this is basic 101 in creative work, we need to do our research and we always uses references and other ideas to tweak and make it our own, we are always a sea of reference turned into something unique. What I having problems is to take 1 or 2, 3 parts of this process and focus too much on that, and worst of all, none of this parts are the unique imput of the designers, writers and artists.

Second addendum (sorry): From what I saw about people defending it, and those who use this referencing approach, one thing I realize is that almost all of the cases it's better for them to explain directly what their game are going to be, when they throw references usually end up is something incoherent that opens to a lot of interpretations that will be very far from what the game it it. And people defending most times than not goes with the argument that when talking and recommending to someone, using references helps, and this is call anecdotal evidence, when you use a personal story to exemplified a general idea, and first this isn't work, and second you can't compare personal talking with friends and colleagues with market campaign, they have different language and approach.

Third Addendum (...) : I didn't find any research or study that shows that this approach is benefical for the designers, that improve their reach and sales, I know it makes sense for sites that covers tabletop rpg due to the need to play wiht algorithm and SEO but for designers I wouldn't be surprised if this is just a concept they accept without put too much thought. The tabletop rpg scene, specially indie is usually overly hostile to marketing concepts, and in this case they could be automatically applying a market concept that might give the big reach they think it gives, but I would need to know some numbers to be sure.

Thank you.

Raul.

[blubberquark]

Share Your Anecdotes: Multicore Pessimisation

I took a look at the specs of new 7000 series Threadripper CPUs, and I really don't have any excuse to buy one, even if I had the money to spare. I thought long and hard about different workloads, but nothing came to mind.

Back in university, we had courses about map/reduce clusters, and I experimented with parallel interpreters for Prolog, and distributed computing systems. What I learned is that the potential performance gains from better data structures and algorithms trump the performance gains from fancy hardware, and that there is more to be gained from using the GPU or from re-writing the performance-critical sections in C and making sure your data structures take up less memory than from multi-threaded code. Of course, all this is especially important when you are working in pure Python, because of the GIL.

The performance penalty of parallelisation hits even harder when you try to distribute your computation between different computers over the network, and the overhead of serialisation, communication, and scheduling work can easily exceed the gains of parallel computation, especially for small to medium workloads. If you benchmark your Hadoop cluster on a toy problem, you may well find that it's faster to solve your toy problem on one desktop PC than a whole cluster, because it's a toy problem, and the gains only kick in when your data set is too big to fit on a single computer.

The new Threadripper got me thinking: Has this happened to somebody with just a multicore CPU? Is there software that performs better with 2 cores than with just one, and better with 4 cores than with 2, but substantially worse with 64? It could happen! Deadlocks, livelocks, weird inter-process communication issues where you have one process per core and every one of the 64 processes communicates with the other 63 via pipes? There could be software that has a badly optimised main thread, or a badly optimised work unit scheduler, and the limiting factor is single-thread performance of that scheduler that needs to distribute and integrate work units for 64 threads, to the point where the worker threads are mostly idling and only one core is at 100%.

I am not trying to blame any programmer if this happens. Most likely such software was developed back when quad-core CPUs were a new thing, or even back when there were multi-CPU-socket mainboards, and the developer never imagined that one day there would be Threadrippers on the consumer market. Programs from back then, built for Windows XP, could still run on Windows 10 or 11.

In spite of all this, I suspect that this kind of problem is quite rare in practice. It requires software that spawns one thread or one process per core, but which is deoptimised for more cores, maybe written under the assumption that users have for two to six CPU cores, a user who can afford a Threadripper, and needs a Threadripper, and a workload where the problem is noticeable. You wouldn't get a Threadripper in the first place if it made your workflows slower, so that hypothetical user probably has one main workload that really benefits from the many cores, and another that doesn't.

So, has this happened to you? Dou you have a Threadripper at work? Do you work in bioinformatics or visual effects? Do you encode a lot of video? Do you know a guy who does? Do you own a Threadripper or an Ampere just for the hell of it? Or have you tried to build a Hadoop/Beowulf/OpenMP cluster, only to have your code run slower?

I would love to hear from you.

[finotica]

Cryptocurrency and Blockchain Technology: A Comprehensive Guide

In recent years, cryptocurrency and blockchain technology have revolutionized the way we think about finance, security, and even the internet itself. While both of these concepts might seem complex at first glance, they hold immense potential to reshape industries, enhance security, and empower individuals globally. If you’ve ever been curious about the buzz surrounding these digital innovations, you’ve come to the right place.

In this article, we will break down what cryptocurrency and blockchain technology are, how they work, and the various ways they are being used today. By the end, you’ll have a solid understanding of these cutting-edge topics and why they are so important in the modern world.

1. What is Cryptocurrency?

At its core, cryptocurrency is a type of digital currency that uses cryptography for security. Unlike traditional currencies issued by governments (such as dollars or euros), cryptocurrencies are decentralized and typically operate on a technology called blockchain. Cryptocurrencies are designed to function as a medium of exchange, and they offer a new way of conducting secure financial transactions online without the need for a central authority like a bank.

The most well-known cryptocurrency is Bitcoin, but there are thousands of other cryptocurrencies, such as Ethereum, Litecoin, and Ripple, each with its own unique features and use cases.

2. How Does Cryptocurrency Work?

Cryptocurrencies operate on decentralized networks using blockchain technology. Each transaction made with a cryptocurrency is recorded in a public ledger known as the blockchain. This ledger is maintained by a network of computers called nodes, which verify and confirm each transaction through complex algorithms.

What makes cryptocurrency unique is its decentralized nature. Since there is no central authority controlling the currency, users have more control over their funds. This also provides an added layer of security, as the system is resistant to hacking and fraud.

3. The Birth of Bitcoin: The First Cryptocurrency

In 2008, an unknown person or group using the pseudonym Satoshi Nakamoto introduced Bitcoin to the world. Nakamoto published a white paper titled “Bitcoin: A Peer-to-Peer Electronic Cash System” that outlined the principles of what we now know as Bitcoin.

Bitcoin became the first decentralized cryptocurrency, and it offered a solution to some of the flaws of traditional financial systems, such as high fees, slow transaction times, and reliance on third parties. Since its inception, Bitcoin has grown to become the most widely recognized and valuable cryptocurrency.

4. Blockchain Technology: The Backbone of Cryptocurrency

Blockchain technology is what makes cryptocurrencies possible. A blockchain is a distributed ledger that records transactions across multiple computers. Once data is recorded on the blockchain, it is extremely difficult to alter or delete, making it highly secure and immutable.

Each block in the chain contains a cryptographic hash of the previous block, a timestamp, and transaction data. This interconnected structure ensures that the data is secure and tamper-proof. Blockchain technology isn’t limited to cryptocurrencies; it has a wide range of applications, from supply chain management to healthcare.

5. How Does Blockchain Work?

To put it simply, a blockchain is a chain of blocks, where each block represents a set of data. When a new transaction is made, that transaction is added to a block, and once the block is complete, it is added to the chain.

The process of validating these transactions is carried out by miners (in proof-of-work systems) or validators (in proof-of-stake systems). These participants ensure that the transaction data is correct and consistent across the entire network.

The decentralized nature of blockchain means that no single entity controls the ledger. This makes it highly resistant to manipulation, and it creates a more transparent system of record-keeping.

6. The Advantages of Blockchain Technology

Blockchain technology offers a wide range of benefits, which is why it has gained so much traction across various industries. Here are some key advantages:

Security: Blockchain is designed to be secure. Each transaction is encrypted and linked to the previous one, making it nearly impossible to alter data without detection.

Transparency: The decentralized nature of blockchain allows for full transparency. All participants in the network can see and verify transactions.

Efficiency: Traditional financial systems can be slow and costly. Blockchain allows for faster transactions at lower fees by cutting out intermediaries.

Decentralization: Blockchain is not controlled by a single entity, giving users more autonomy over their data and transactions.

7. Common Applications of Blockchain Technology

While blockchain technology is best known for its use in cryptocurrency, it has a variety of other applications. Here are a few examples:

Finance: Beyond cryptocurrencies, blockchain is being used in the financial sector to streamline processes like cross-border payments, loans, and insurance claims.

Supply Chain Management: Blockchain can improve transparency and efficiency in supply chains by providing a tamper-proof record of each step in the production process.

Healthcare: Blockchain can be used to securely store and share patient data, ensuring that medical records are accurate and up to date.

Voting Systems: Blockchain has the potential to revolutionize voting by providing a secure and transparent platform for casting and counting votes.

8. Popular Cryptocurrencies Beyond Bitcoin

While Bitcoin was the first cryptocurrency, many others have since been developed, each with its own unique use cases. Here are some of the most popular:

Ethereum: Ethereum is more than just a cryptocurrency; it is a platform for creating decentralized applications (DApps) and smart contracts.

Litecoin: Often referred to as the silver to Bitcoin’s gold, Litecoin is a peer-to-peer cryptocurrency designed for faster transaction times.

Ripple (XRP): Ripple is a digital payment protocol that enables fast, low-cost international money transfers.

Cardano: A proof-of-stake blockchain platform that aims to provide a more secure and scalable way to handle transactions.

9. The Risks and Challenges of Cryptocurrency and Blockchain

As with any technology, there are risks and challenges associated with cryptocurrency and blockchain. Here are some of the key concerns:

Volatility: Cryptocurrencies are known for their price volatility, which can result in significant gains or losses for investors.

Regulation: The regulatory environment for cryptocurrencies is still evolving, and different countries have varying approaches to how they govern digital currencies.

Security Risks: While blockchain is highly secure, the wallets and exchanges used to store and trade cryptocurrencies can be vulnerable to hacking.

Environmental Impact: Some cryptocurrencies, such as Bitcoin, require large amounts of energy for mining, leading to concerns about their environmental impact.

10. The Future of Cryptocurrency and Blockchain Technology

The future of cryptocurrency and blockchain technology looks bright, but there are still many uncertainties. As more governments, companies, and individuals adopt these technologies, we can expect to see continued innovation and development.

Some experts predict that blockchain will become the standard for secure, decentralized systems across a wide range of industries, while others believe that cryptocurrencies will become a mainstream form of payment. Regardless of what the future holds, it is clear that both blockchain and cryptocurrency will play a significant role in shaping the digital landscape.

Conclusion

In summary, cryptocurrency and blockchain technology have already made a profound impact on the world of finance and technology. Cryptocurrencies like Bitcoin and Ethereum have given individuals more control over their money, while blockchain has provided a secure and decentralized way to store data.

While there are risks and challenges, the potential benefits of these technologies are enormous, and they are only just beginning to be realized. Whether you’re an investor, a tech enthusiast, or just curious about the future, staying informed about cryptocurrency and blockchain is essential.

By understanding the fundamentals of how these systems work, you can position yourself to take advantage of the opportunities they offer in the years to come.

To learn more in-depth about how cryptocurrency and blockchain technology can impact your financial future, click here to explore our full guide on Finotica: Read More. Discover expert insights, practical tips, and the latest trends to stay ahead in the digital finance revolution!