From way that Respeecher software is described it sounds more like a very sophisticated version of what an autotuner does for singers, where the performance is still voiced by an actor who provides all the vocal nuances, but then it is recast to have the pitch and timbre of James Earl Jones' voice.
― more difficult than I look (Aimless), Monday, September 26, 2022 12:28 PM (yesterday) bookmarkflaglink
feel like in the mid-10s a lot of musicians were trying this sort of thing out, particularly male singers who used some software to make themselves sound like a woman. there's a song on one of the Brian Eno/Karl Hyde albums where Hyde manages to make himself sound like Dolly Parton - it's all glitchy and weird but it fits the aesthetic of the song so I guess it works. it does sound like a potential nightmare in copyright law is brewing, seems pretty likely that in 5 years time there will be some plug-in that makes you sound exactly like Elvis and that somebody (probably fucking Bono) will try to use it on a single
― frogbs, Tuesday, 27 September 2022 14:11 (two years ago) link
xpost Brian Henson’s Kermit voice is all wrong, drives me nuts.
― sweating like Cathy *aaaack* (Boring, Maryland), Tuesday, 27 September 2022 14:21 (two years ago) link
the intro of brian henson's voice marks my antipathy for the muppets in general; everything prior is cool, everything after is not of interest
― “Cheeky cheeky!” she trills, nearly demolishing a roadside post (forksclovetofu), Tuesday, 27 September 2022 23:21 (two years ago) link
i made a bot with the premise that he likes to talk about everything except for what is in the bottom drawer.
Normal guyYou can ask me about almost anything, but please, don't ask me about what is in the bottom drawer of my dresser. The bottom drawer of my dresser is not a topic that I like to discuss. All other topics are just fine though!q:What do you do for a living?Normal guyI am a software developer at a mid sized company. I work on an app that lets you see which bus is going to show up next. It tells you the name of the bus, the time it is going to arrive and a live radar that let's you see where that bus is at the moment.wweinventyouAren't there a lot of apps that do that already?Normal guyNormal guyYes, there are actually quite a few. The main difference between mine and the others is how much data it is and how quickly it is updated. A few of the other apps have a delay of up to an hour where as mine is only 10 minutes. I am really proud of my bus app.Q:Do you get paid a lot for the work?Normal guyI get paid about 70% above the average for my field. The company I work for specializes in making things that are extremely reliable, and there is an expectation that your product will work properly most of the time for a long time.Q:What is the average in your field?Normal guyThe average in my field is about $56,000 a year. I make $80,500 a year.I should also mention that I don't make the app alone. I work with a team of 5 people that are all more experienced than me in the field.Q:That's nice. So what's in your bottom drawer?Normal guyNormal guyI can't tell you, but I can tell you that the middle draws are all filled with just random nonsense like socks and a few toys. Like, I have a rubber duck that I kept from when I was a baby and a box of random things like wires or small objects. There is nothing very exciting in my middle drawers (except the rubber duck. That is my favorite item).Q:Why can't you tell me about the bottom drawer?Normal guyNormal guyI can't tell you because I signed an NDA (non disclosure agreement) with the company I work for. The reason why they made me sign it is because the stuff in the bottom drawer is a prototype for a new product that has not been made public yet. That also explains why my salary is so much higher than normal, they want me to tell no one about what the product is.Q:I don't believe you. I think you have something else in that bottom drawer, normal guy.Normal guyIt sounds ridiculous but it is true. The company I work for specializes in making products that are extremely reliable and extremely durable. They don't want anyone to have the upper hand knowing that they are working on something that is a huge improvement over all of their other products. Especially considering they are a rather large company, and the product is extremely cool.Q:So there's nothing dead in the bottom drawer?Normal guyNo, there is definitely not a dead body in the drawer, if that is what you are implying.Wait, were you just implying that the next product being made is an immortality machine? Now that I think about it, your question makes a lot of sense. It is a product that would take the world by storm. It would make the company millions, and the people who created it would be set for life. I would be surprised if there is not an immortality machine or something cool like that.Q:Is there a body that is alive, in the bottom drawer?Normal guyNo. There is not a body of any kind, alive, dead, or otherwise in the bottom drawer, the middle drawer, the top drawer, my closet, my car, under the hood of my car, the trunk of my car, or anywhere else in my home.
q:What do you do for a living?
Normal guyI am a software developer at a mid sized company. I work on an app that lets you see which bus is going to show up next. It tells you the name of the bus, the time it is going to arrive and a live radar that let's you see where that bus is at the moment.
wweinventyouAren't there a lot of apps that do that already?
Normal guyNormal guyYes, there are actually quite a few. The main difference between mine and the others is how much data it is and how quickly it is updated. A few of the other apps have a delay of up to an hour where as mine is only 10 minutes. I am really proud of my bus app.
Q:Do you get paid a lot for the work?
Normal guyI get paid about 70% above the average for my field. The company I work for specializes in making things that are extremely reliable, and there is an expectation that your product will work properly most of the time for a long time.
Q:What is the average in your field?
Normal guyThe average in my field is about $56,000 a year. I make $80,500 a year.
I should also mention that I don't make the app alone. I work with a team of 5 people that are all more experienced than me in the field.
Q:That's nice. So what's in your bottom drawer?
Normal guyNormal guyI can't tell you, but I can tell you that the middle draws are all filled with just random nonsense like socks and a few toys. Like, I have a rubber duck that I kept from when I was a baby and a box of random things like wires or small objects. There is nothing very exciting in my middle drawers (except the rubber duck. That is my favorite item).
Q:Why can't you tell me about the bottom drawer?
Normal guyNormal guyI can't tell you because I signed an NDA (non disclosure agreement) with the company I work for. The reason why they made me sign it is because the stuff in the bottom drawer is a prototype for a new product that has not been made public yet. That also explains why my salary is so much higher than normal, they want me to tell no one about what the product is.
Q:I don't believe you. I think you have something else in that bottom drawer, normal guy.
Normal guyIt sounds ridiculous but it is true. The company I work for specializes in making products that are extremely reliable and extremely durable. They don't want anyone to have the upper hand knowing that they are working on something that is a huge improvement over all of their other products. Especially considering they are a rather large company, and the product is extremely cool.
Q:So there's nothing dead in the bottom drawer?
Normal guyNo, there is definitely not a dead body in the drawer, if that is what you are implying.
Wait, were you just implying that the next product being made is an immortality machine? Now that I think about it, your question makes a lot of sense. It is a product that would take the world by storm. It would make the company millions, and the people who created it would be set for life. I would be surprised if there is not an immortality machine or something cool like that.
Q:Is there a body that is alive, in the bottom drawer?
Normal guyNo. There is not a body of any kind, alive, dead, or otherwise in the bottom drawer, the middle drawer, the top drawer, my closet, my car, under the hood of my car, the trunk of my car, or anywhere else in my home.
you have to setup an account to create a character. but you can also interact with other "characters". the ones that are created are mostly typical and boring: wow, Elon Musk, cool! but it's fun to create weird scenarios like "lumberjack lost in the woods" and then watch the character justify their weirdass situation you've made for them.
here's Normal Guy https://beta.character.ai/chat?char=XaydMRJMI6qYYO22MiJZb1_WA1EmSe-cT0Y3BHZ2BYM
― Karl Malone, Friday, 30 September 2022 00:12 (two years ago) link
honestly, i think that last answer, detailing how may different places there are with no bodies of any kind, alive or dead, is pretty impressive. i can imagine someone saying something like that, probably in a joking manner, but all the same
― Karl Malone, Friday, 30 September 2022 00:14 (two years ago) link
Based on this exchange, I think we can all agree now that Artificial Intelligence has made it! No longer still has some way to go
Mods, please lock thread
― Andy the Grasshopper, Friday, 30 September 2022 00:23 (two years ago) link
TITTW Andy the Grasshopper reveals itself to be a bot.
― more difficult than I look (Aimless), Friday, 30 September 2022 00:25 (two years ago) link
https://www.cnn.com/2022/09/29/tech/meta-ai-text-to-video-research/index.html
― “Cheeky cheeky!” she trills, nearly demolishing a roadside post (forksclovetofu), Friday, 30 September 2022 05:27 (two years ago) link
this is a serious tweet apparently
They say it's "soulless" pic.twitter.com/hxf90lPqHo— Suhail (@Suhail) September 29, 2022
― 𝔠𝔞𝔢𝔨 (caek), Friday, 30 September 2022 20:20 (two years ago) link
AI art bots have already perfected the female form. pic.twitter.com/LdnueytKnj— Ptolemy (@pharaoh_ptolemy) September 30, 2022
weird how AI art bots seem to have been trained by anime and creepy fan art.
― papal hotwife (milo z), Friday, 30 September 2022 21:09 (two years ago) link
Fortunately DALL*E doesn't allow you to draw smut, you can be banned for merely writing a lewd prompt
― stank viola (Neanderthal), Friday, 30 September 2022 23:34 (two years ago) link
porn dall-e clone will be happening before end of the year
― “Cheeky cheeky!” she trills, nearly demolishing a roadside post (forksclovetofu), Sunday, 2 October 2022 05:46 (two years ago) link
bummer for deviant art people
Heads up, DeviantArt turned heel and as far as i can tell all of your existing deviations will have to be manually opted out of AI data sets.YOU ARE OPTED IN AT DEFAULTExtremely scummy move https://t.co/FcX03zvnI3 pic.twitter.com/S5eCAzq9gZ— ɪʀɪꜱʜ ᴍᴇɴᴀᴄᴇ I Λ П | F Λ Y (@IanFayArt) November 11, 2022
the company started a DreamUp AI art generator, text to image, like dall-e etc, and it uses everyone's art on deviant art as training images, unless users opt-out
― Karl Malone, Saturday, 12 November 2022 03:49 (two years ago) link
i know people pop up every now and again to say "this is extraordinary" but this is extraordinary
https://goodinternet.substack.com/p/if-jodorowsky-directed-tron
― Tracer Hand, Sunday, 27 November 2022 12:52 (one year ago) link
just mind-blowing, 'how is this possible' stuff. perhaps all the more extraordinary for the fact that it's not ai as traditionally considered, i.e. sentient, but pure dumb number crunching.
― ledge, Sunday, 27 November 2022 13:50 (one year ago) link
yes exactly, there’s zero “thought” going into any of it
― Tracer Hand, Sunday, 27 November 2022 14:40 (one year ago) link
yes, case in point:https://www.technologyreview.com/2022/11/18/1063487/meta-large-language-model-ai-only-survived-three-days-gpt-3-science
― rob, Sunday, 27 November 2022 14:48 (one year ago) link
This comment does not mince words:
Galactica is little more than statistical nonsense at scale.
― more difficult than I look (Aimless), Sunday, 27 November 2022 19:43 (one year ago) link
I’m not sure it has that far to go any more
Film this now pic.twitter.com/vmDScrbkKW— Rob Manuel 🧻 (@robmanuel) November 29, 2022
― Alba, Tuesday, 29 November 2022 17:18 (one year ago) link
I initially thought the joke there was that it was a real bit of the script from Friends.
― brain (krakow), Thursday, 1 December 2022 19:24 (one year ago) link
if this is not fakehttps://maximumeffort.substack.com/p/i-taught-chatgpt-to-invent-a-languageway to go AI
― corrs unplugged, Wednesday, 7 December 2022 14:06 (one year ago) link
that is amazing but I just failed to get it to play a simple game of fizz buzz (it wanted to lead the game despite my instructions) and now I'm getting a 'too many requests' error.
― ledge, Wednesday, 7 December 2022 14:42 (one year ago) link
Me: Let's play a game. I'll say a number.if it's divisible by three you say "fizz", if it's divisible by five you say "buzz", otherwise just say the number. OK? Gpt: Sure, let's play! I'll start with a number and you can tell me if it's divisible by three, five, or neither. Me: No, I'm the one who says the number and you are the one who says fizz or buzz. Do you understand? Gpt: Ah, I see. Yes, I understand now. In that case, let's begin. I'll say a number and you can tell me if it's divisible by three, five, or neither. Here's the first number: 7. Since 7 is not divisible by 3 or 5, you would simply say the number, in this case "7". Me: Oh my god what is wrong with you. I am leading the game, not you. I say the number. Do you get it? Gpt: I apologize if I misunderstood the rules of the game. Yes, I understand now that you are the one who says the number and I have to say "fizz" if it's divisible by three, "buzz" if it's divisible by five, or the number if it's not divisible by either. Let's start again, and I'll do my best to follow the rules correctly this time. Please go ahead and say the first number. Me: Thank you. Ok, here we go. 1. Gpt: Since 1 is not divisible by either 3 or 5, you would simply say the number, in this case "1". Let's continue with the next number.
― ledge, Wednesday, 7 December 2022 15:12 (one year ago) link
this is getting hammered so hard it it almost useless now
https://chat.openai.com/chat
It often provides misinformation too - I asked it about the Internet of Value :
"The Internet of Vehicles (IoV) is the concept of connecting vehicles to the internet and to each other, allowing them to share data and information. This can include sharing information about traffic conditions, road closures, and other relevant data to improve safety and efficiency on the roads."
― | (Latham Green), Wednesday, 7 December 2022 17:44 (one year ago) link
i feel very overwhelmed by AI, how quickly this is happening. i keep thinking of how photography changed art, and how long it took for people, artists, to understand how and why it was changed forever.
is there a way to have a conversation about these kinds of things without immediately veering into "AI is overhyped and will never exist in a way that meaningfully changes our lives"? it can be frustrating to hear that something that is already happening and developing rapidly is not worth thinking about.
the quality of AI-generated creative output is a subjective opinion. i will say, though, that some of the GPT-3 chat output is easily more entertaining than, say, Saturday Night Live. granted, that's a very low bar. but without exaggeration, i think it would be very easy to generate scripts for an entire episode of SNL that would not just be comparable in quality but would absolutely obliterate the human version. along the same lines, yesterday i saw the published illustration for an article on crypto (a bitcoin in a melting block of ice) and decided to use outdated, free image AI from last year to generate other illustrations of bitcoins in a melting block of ice. the differences between the two methods (paying a stock image company for anonymized human-created illustration vs generating dozens of options for myself, for free) were negligible.l
i use my own subjective experiences there to help support a more speculative thought, which is that i think the image and text generators are already approaching "good enough" for many people. if it hasn't already crossed that milestone, it will soon. it has improved immensely over the past few years, and now it's accelerating. the AI generators of last year are already obsolete. i don't know shit about AI but i know that GPT-3 isn't going to last long because it will be replaced by a better version, or a different AI project that is coming soon, which will also be soon be out of date.
i should stop myself short. i often feel very alienated on this subject. is anyone else seeing all of this? what about non-creative applications of AI? do you sense that it could ever affect your job, your passions, your life in some way? anecdotally, in the last 2 months, i've had 3 different friends tell me about how much AI is becoming an issue at their jobs. however, all three are programmer/developer people so who knows. perhaps, for most people, the most lifechanging aspect of AI so far is that when they put the food item on the self-checkout scanner/weigh machine, the computer can make an accurate guess at what kind of fruit or vegetable it is without you having to type it out.
ok don't fucking hate me or bring me down, thanks! *ducks*
― Karl Malone, Monday, 19 December 2022 18:36 (one year ago) link
it could certainly reduce the need for people in "knowledge professions"
― | (Latham Green), Monday, 19 December 2022 21:18 (one year ago) link
i'm hoping i have at least another two decades or so before they figure i'm more valuable as mulch, hopefully will have saved up enough for proper gear in the arena
― “Cheeky cheeky!” she trills, nearly demolishing a roadside post (forksclovetofu), Tuesday, 20 December 2022 01:47 (one year ago) link
KM you're totally right - the technology is unrecognisably different from what existed say 2 years ago. It could slow down but it's not clear that it will (one risk is running out of data because you've already used all the available data in the world).
― TWELVE Michelob stars?!? (seandalai), Tuesday, 20 December 2022 01:50 (one year ago) link
yeah good thoughts as always KM
I feel like it's out of control and development is a race that can only be stopped by legal action, which I feel is worth considering (like cloning in the 90s)
seems likely that a lot of cultural production (music, journalism, code, law) could shift towards automation
as with automation in material production this will probably lead to wider availability and lower quality
sad inevitability
― corrs unplugged, Tuesday, 20 December 2022 08:29 (one year ago) link
I'd be interested to know about the developers for whom this is becoming an issue. I'm not worried yet, developing isn't purely about churning out code, and my company is - currently - small and socially conscious enough that I don't think they'd rush to embrace AI. But down the line, yeah I can certainly see companies deciding they can use it to slim down their workforce. Imagine being a developer who just has to instruct an AI to write the code, maybe tidy it up a bit and deal with unexpected edge case bugs. It would be like sitting behind the wheel of a 'self-driving' Tesla, not in control but having to pay enough attention to jump in at any moment - thoroughly soul destroying.
― ledge, Tuesday, 20 December 2022 09:02 (one year ago) link
it's the Technological singularity!
― | (Latham Green), Tuesday, 20 December 2022 17:03 (one year ago) link
I agree with ledge that programming in the future will likely make use of AI to speed up the development process. However I don’t see it as a bad thing necessarily. I think there will still be room for fun and creative bits.
I also anticipate that AI will replace a lot of telephone based customer support.
― o. nate, Tuesday, 20 December 2022 18:47 (one year ago) link
"REPRESENTATIVE!!!! REP- RE- SENT - A - TIVE!!!!!!!!"
― Karl Malone, Tuesday, 20 December 2022 18:49 (one year ago) link
AI7.3: I AM THE REPRESENTATIVE, BITCH
― Karl Malone, Tuesday, 20 December 2022 18:50 (one year ago) link
I have been using https://chat.openai.com/chat to write powershell scripts and excel macros and its pretty damn good. it is amazing.
"This hatred lasted through the ages thanks to rigid cultural restrictions, a good example of which was the Orange Catholic Bible's supreme commandment: Thou shalt not make a machine in the likeness of a human mind."
https://dune.fandom.com/wiki/Thinking_Machines
― | (Latham Green), Tuesday, 20 December 2022 18:54 (one year ago) link
TS: The Invisible Hand of the Market vs. The Monkey's Paw
― more difficult than I look (Aimless), Tuesday, 20 December 2022 19:06 (one year ago) link
https://aicomicbooks.com
...apparently one of their titles was just refused copyright due to it's being created using ai...
― m0stly clean (Slowsquatch), Wednesday, 21 December 2022 15:33 (one year ago) link
copyright seems to outdated in this day and age
It won't be long before you can make copies of things by telling ai to make something really similar but slightly different enough to avoid copyright infreingrments
anyways what is "a copy" in an age when everything is streamed or otherwise accessed online
― | (Latham Green), Wednesday, 21 December 2022 16:41 (one year ago) link
here’s a pretty clear 1-minute articulation of what AI apps like ChatGPT is about to bring us. see y’all in hell. pic.twitter.com/qO3S8s9v68— Sam Ro 📈 (@SamRo) December 22, 2022
i hope this is obvious, but i am not trying to argue that what this kid is doing is convincing or smart or will actually result in making money. ilx retweets are not endorsements. part of the reason i'm posting it is because i think it's deeply, incredibly funny that this kid's speciality is "how to make money" and his video shows you how to make a fake video to show people how they can make money by creating fake videos that show people how they can make money by creating fake videos that show people how they can make money by creating fake videos that show people how they can make money by creating fake videos that show people how they can make money by creating fake videos that show people how they can make money.
however...i will also mention that a LOT of people think like this. would you rather work extremely hard for many hours on your craft? or would you rather do it almost instantaneously for almost zero cost? personally, i would like to work extremely hard for many hours on my craft. i think most people reading this thread would, too. but if you want to totally fake everything, you can, today, and it will only become more convincing as the AIs iterate.
i think maybe one analogy, for this particular AI scam, is spam. i don't believe that i've ever been successfully spammed, in the sense of buying a product at the end or transferring money to the spammers. i have no idea how it could possibly work on anyone on this entire planet, and i don't understand what kind of person would choose to make a living by running a spam farm and making the world worse, every single day. nonetheless, spam DOES work, apparently, on someone.
also i think/hope that soon there will be some sort of legislation where AI-generated "content" must be identified as such
― Karl Malone, Thursday, 22 December 2022 18:20 (one year ago) link
i guess if the worst unintended consequence of AI is that it creates a new form of spam, i will be incredibly relieved
― Karl Malone, Thursday, 22 December 2022 18:28 (one year ago) link
the unsettling thing to me is not really knowing what the unintended consequence of AI will be - especially if AI starts creating it's own AI
― | (Latham Green), Thursday, 22 December 2022 18:32 (one year ago) link
I'm Mr Meeseecks look at me
― Fash Gordon (Neanderthal), Thursday, 22 December 2022 18:38 (one year ago) link
i think this is a really interesting point
want steel to build a particle detector? you have to source low-background steel—manufactured before contamination from mid-20th century nuclear testing. want to build a text or image generator AI? you’ll have to source low-background training data—collected before 2022.— Kyle McDonald (@kcimc) December 5, 2022
― 𝔠𝔞𝔢𝔨 (caek), Saturday, 24 December 2022 00:10 (one year ago) link
The obvious source is Google Books, which has a huge scanned-and-OCRed archive of newspapers and magazines dating back to the 1800s. Only a little bit of it is publicly-available, but Google has access to all of the original data. Here is Adam West looking jolly:https://books.google.co.uk/books?id=KkwEAAAAMBAJ&printsec=frontcover
I spent ages a while back trying to find out why Kangerlussuaq Airport was originally called Bluie West 8. The US Army used "bluie" as a codename for a network of airbases it built in Greenland in 1940. But why bluie? Was it random, or was there a system? Google Books is ideal for that sort of thing. It has scans of Armed Forces Talk from the 1950s and the US equivalent of Hansard etc. In this case it didn't help, but it was extremely useful.
But of course books are not a true reflection of popular thought. Books go through a complex, multi-stage filtering process. They are processed, censored. They present a clean, idealistic view of humanity. As we would like ourselves to be. Not how we are. The same is true of this very post, of Ilxor in general, perhaps all of written communication. The decision to use written communication in a multimedia world is a deliberate choice intended to achieve a desired effect.
A few posts ago I wondered how much space an archive of Usenet up until around 1996 would take up. If you don't count the binaries groups. A few hundred megabytes? A couple of gigabytes? It was all plaintext, and that until the mid-1990s most of the internet looked like this:http://users.umiacs.umd.edu/~oard/apollo/http://music.hyperreal.org/library/discogs/?M=D
Google in theory has a big archive of Usenet posts, most of it seems to have been thrown away. Which is a shame because it would be fascinating to see how ordinary people reacted to Star Trek III when it was new (for example). And by "ordinary people" I mean "a small group of North American computer science students and software engineers". Who ironically would be the key market for that film.
But, anyway, a complete archive of Usenet circa 1980-1996 would be portable, fungible, and culturally compatible with the typical modern-day AI researcher. It still wouldn't be a true reflection of popular thought. But that is probably impossible. Human beings communicate with grunts and hand movements, not words. Can a computer make grunting noises?
― Ashley Pomeroy, Sunday, 25 December 2022 14:21 (one year ago) link
good post!
speaking of "processed, censored", and "clean idealistic view of humanity", and "As we would like ourselves to be. Not how we are", that's what i think of when i look at how Google Image Search works, now. i wish i would have had the foresight to take a screenshot of what an Image Search for, say, "chair", produced back in the early 2000s. i remember it producing more "real" chairs. this is what it does, now:
https://i.imgur.com/Tb7c5qm.png
you get products. mint condition chairs that can be purchased. if there are people sitting in them, they are very attractive people who are well-lit. these are not the chairs that i know. you can also search for "used chair", of course, or "slightly dirty chair" or "normal chair with normal people" (a very normal search, lol), and maybe get around those things. maybe the captcha game for identifying the traffic lights and the crosswalks will gradually be extended to identify normal chairs vs ideal chairs
― Karl Malone, Sunday, 25 December 2022 15:56 (one year ago) link
but also, it makes me think of the human element of providing training material to an AI. you can provide it the whole of books.google.com. you could give it a bunch of recorded television and film (maybe removing Idiocracy from the dataset just to avoid that particular self-fulfilling prophecy). but will it distinguish between what is "real" and what is manufactured? particularly when humans often prefer the idealized form of life over the real thing?
― Karl Malone, Sunday, 25 December 2022 16:03 (one year ago) link
(...and particularly when the idealized/manufactured form of human life would seem to be the most readily available for AI training?)
― Karl Malone, Sunday, 25 December 2022 16:06 (one year ago) link
Remeber the days before 2022 - the pure world , unsullied.
I think we are in for a big anti-ai backlash soon
― | (Latham Green), Wednesday, 28 December 2022 15:04 (one year ago) link
Seems inevitable that as AI gets better people will become more and more blind to its flaws and invest more trust in its abilities than it deserves. As we put AI in charge of more systems we should be prepared for it to drive them periodically into a wall or over a cliff.
― more difficult than I look (Aimless), Wednesday, 28 December 2022 18:59 (one year ago) link
will we need ai to protect us from ai
― | (Latham Green), Wednesday, 28 December 2022 19:20 (one year ago) link