Artificial intelligence still has some way to go

porn dall-e clone will be happening before end of the year

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 DEFAULT

Extremely 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

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

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.

yes exactly, there’s zero “thought” going into any of it

yes, case in point:
https://www.technologyreview.com/2022/11/18/1063487/meta-large-language-model-ai-only-survived-three-days-gpt-3-science

This comment does not mince words:

Galactica is little more than statistical nonsense at scale.

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

I initially thought the joke there was that it was a real bit of the script from Friends.

if this is not fake
https://maximumeffort.substack.com/p/i-taught-chatgpt-to-invent-a-language
way to go AI

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.

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.

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."

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*

it could certainly reduce the need for people in "knowledge professions"

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

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).

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

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.

it's the Technological singularity!

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.

"REPRESENTATIVE!!!! REP- RE- SENT - A - TIVE!!!!!!!!"

AI7.3: I AM THE REPRESENTATIVE, BITCH

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

TS: The Invisible Hand of the Market vs. The Monkey's Paw

https://aicomicbooks.com

...apparently one of their titles was just refused copyright due to it's being created using ai...

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

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

i guess if the worst unintended consequence of AI is that it creates a new form of spam, i will be incredibly relieved

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

I'm Mr Meeseecks look at me

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

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?

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.

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

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?

(...and particularly when the idealized/manufactured form of human life would seem to be the most readily available for AI training?)

Remeber the days before 2022 - the pure world , unsullied.

I think we are in for a big anti-ai backlash soon

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.

will we need ai to protect us from ai

Irl lol at the mention of Idiocracy

I do think at some point we reach the limits of human mental ability and have to use ai to go further. Especially writing software look at all this inferior garbage these days - also probably replacing most managers with as would be a notable improvement * sorry to be grouchy

"i remember it producing more "real" chairs"

And of course if you search for e.g. "tagliatelle" Google just returns page after page of links to recipe sites with tagliatelle recipes. And yet if I search for "difference tagliatelle fettuccine" Google does return useful results, so perhaps I'm just being crap.

The subject of perfect people in perfect homes makes me wonder if any police forces have tried feeding a database of mugshots into an AI engine in order to generate "the face of a typical criminal". I could imagine it being treated as a joke - "do you look like a crook? click here to find out" - but on the other hand suppose the government of e.g. Myanmar decides that you really can tell whether someone is anti-social just by matching the shape of their face against a set of AI-generated faces. Like a modern-day version of phrenology.

My hunch is that perhaps as a joke at least one insurance company with access to mugshots or passport photos or driving licence photos etc has fed the results into an AI to look for patterns, or to generate generic faces. Wasn't there a website a while back that could generate generic LinkedIn profile faces?

The subject of perfect people in perfect homes makes me wonder if any police forces have tried feeding a database of mugshots into an AI engine in order to generate "the face of a typical criminal". I could imagine it being treated as a joke - "do you look like a crook? click here to find out" - but on the other hand suppose the government of e.g. Myanmar decides that you really can tell whether someone is anti-social just by matching the shape of their face against a set of AI-generated faces. Like a modern-day version of phrenology.

unfortunately, something of the sort is already taking place. not by using facial characteristics (that i know of), but by using other data instead. i don't know how far beyond china the practice extends.

https://www.nytimes.com/2022/06/25/technology/china-surveillance-police.html

The latest generation of technology digs through the vast amounts of data collected on their daily activities to find patterns and aberrations, promising to predict crimes or protests before they happen. They target potential troublemakers in the eyes of the Chinese government — not only those with a criminal past but also vulnerable groups, including ethnic minorities, migrant workers and those with a history of mental illness.

They can warn the police if a victim of a fraud tries to travel to Beijing to petition the government for payment or a drug user makes too many calls to the same number. They can signal officers each time a person with a history of mental illness gets near a school.

...In 2017, one of China’s best-known entrepreneurs had a bold vision for the future: a computer system that could predict crimes.
The entrepreneur, Yin Qi, who founded Megvii, an artificial intelligence start-up, told Chinese state media that the surveillance system could give the police a search engine for crime, analyzing huge amounts of video footage to intuit patterns and warn the authorities about suspicious behavior. He explained that if cameras detected a person spending too much time at a train station, the system could flag a possible pickpocket.

“It would be scary if there were actually people watching behind the camera, but behind it is a system,” Mr. Yin said. “It’s like the search engine we use every day to surf the internet — it’s very neutral. It’s supposed to be a benevolent thing.”

He added that with such surveillance, “the bad guys have nowhere to hide.”

Five years later, his vision is slowly becoming reality. Internal Megvii presentations reviewed by The Times show how the start-up’s products assemble full digital dossiers for the police.

“Build a multidimensional database that stores faces, photos, cars, cases and incident records,” reads a description of one product, called “intelligent search.” The software analyzes the data to “dig out ordinary people who seem innocent” to “stifle illegal acts in the cradle.”

A Megvii spokesman said in an emailed statement that the company was committed to the responsible development of artificial intelligence, and that it was concerned about making life more safe and convenient and “not about monitoring any particular group or individual.”

2002: Don't be evil
2022: It's supposed to be a benevolent thing

i know there's a chatGPT thread but i suppose it makes sense to keep this kind of talk/news in here:

For some students, the temptation is obvious and enormous. One senior at a Midwestern school, who spoke on the condition of anonymity for fear of expulsion, said he had already used the text generator twice to cheat on his schoolwork. He got the idea after seeing people expound on Twitter about how powerful the word generator is after it was released on Nov. 30.

He was staring at an at-home computer-science quiz that asked him to define certain terms. He put them into the ChatGPT box and, almost immediately, the definitions came back. He wrote them by hand onto his quiz paper and submitted the assignment.

Later that day, he used the generator to help him write a piece of code for a homework question for the same class. He was stumped, but ChatGPT wasn’t. It popped out a string of text that worked perfectly, he said. After that, the student said, he was hooked, and plans to use ChatGPT to cheat on exams instead of Chegg, a homework help website he’s used in the past.

He said he’s not worried about getting caught because he doesn’t think the professor can tell his answers are computer-generated. He added that he has no regrets.

“It’s kind of on the professor to make better questions,” he said. “Use it to your own benefit. … Just don’t get through an entire course on this thing.”

https://www.washingtonpost.com/education/2022/12/28/chatbot-cheating-ai-chatbotgpt-teachers/

newspaper writer contemplating that this may be the first and last time they're allowed to let an AI write the closing paragraph of their article and it will still be kind of clever:

ChatGPT had its own ideas about the solution. Asked how to confront the possibility of cheating, the bot offered several suggestions: educate students about the consequences of cheating, proctor exams, make questions more sophisticated, give students support they need so they don’t see the need to cheat.

“Ultimately, it is important to communicate clearly with students about your expectations for academic integrity and to take steps to prevent cheating,” the bot explained. “This can help to create a culture of honesty and integrity in your classroom.”

Remeber the days before 2022 - the pure world , unsullied.

Like "Liverpool aren't going to win the Premier League", this thread's title is increasingly testament to the grim longevity of ILX – keep a messageboard going long enough and everything will happen.

I have no idea what AI is and now I’m too afraid to ask.

**“Ultimately, it is important to communicate clearly with students about your expectations for academic integrity and to take steps to prevent cheating,” the bot explained. “This can help to create a culture of honesty and integrity in your classroom.”**

Naturally all tests and essays will have to be on paper with pencils while the teacher watches.

It seems like people are going to be opting out of technology if it gets too out of hand -o- like John in Brave New World

https://i.imgur.com/UFNmhPb.png

can i opt out of this car driving past me