[Manic!]

The AI revolution has brought about a new era of technological advancements, and with it comes a wave of exciting developments. However, amidst these innovations lies a potential threat - the AI apocalypse. Currently, the field of AI is akin to the wild wild west, reminiscent of the early days of the internet where information was exchanged between enthusiasts. Regrettably, the majority of people are unaware of the rapid progress being made in this field. Let me shed some light on the latest developments.

ChatGTP and Plugins

Are you looking to translate a song? Look no further than ChatGTP, which uses cutting-edge AI to translate songs seamlessly. This feature has proven to be particularly effective with Punjabi songs. Moreover, ChatGTP now offers plugins that integrate with other apps. For instance, it can work with grocery delivery apps and plan meals for families based on their preferences. It generates a week's worth of recipes, creates a grocery list, places the order, and sets reminders on your phone. Companies like Hello Fresh could potentially be at risk.

Voice Cloning

While it is commonly known that voices can be cloned, it is now possible to make cloned voices speak in different languages. Dubbing movies into different languages using voice actors could soon be a thing of the past. Instead, AI can take the original audio and generate multiple language versions.

Text to Image

Multiple AI models exist, some of which have no restrictions. It is becoming increasingly difficult to distinguish between real and fake photos.


Made with AI.
https://i.ibb.co/GkWBXnh/asn.png

https://i.ibb.co/7StrTd9/px4.png




Text to Video

While the technology is still in its nascent stage, it is continually improving. Check out this video for a demonstration.
https://www.youtube.com/watch?v=YlY-iNrqFDo

It's clear that the adult industry is set to face challenges ahead. (lots of people will lose jobs.)

This post was made using CHATGTP just pasted a rough draft into it and it did the rest.

Here is a version in donald trumps voice.

Listen folks, let me tell you, this AI thing is a disaster, believe me. It's like the wild wild west out there, just like the early days of the internet, when people didn't know what the heck was going on. Most people have no clue what's happening with AI, but I'm going to tell you, I've done my research.

Now, we've got ChatGTP and plugins, folks. Tremendous technology, let me tell you. You want to translate a song? You give ChatGTP the name and artist, and it's going to translate it for you. It's doing great with Punjabi songs, let me tell you. And now, it can even work with other apps, like grocery delivery apps. It can plan your meals for the week, folks. It's going to generate recipes, create a grocery list, and even send reminders to your phone. Hello Fresh is in trouble, folks.

Voice cloning, believe me, it's a thing. They can even make it speak in different languages, folks. Dubbing movies with voice actors, that's going to be a thing of the past. The technology is just tremendous.

Text to image, it's crazy. Some AI models have no restrictions, folks. It's getting harder and harder to tell what's real and what's fake.

Text to video, it's not perfect, but it's getting better every day, folks. Take a look at this video, it's tremendous.

And let me tell you, the adult industry is in big trouble.

[MarkyMark]

We think the distribution of wealth is getting out of hand now you can imagine 20 years from now where you're relying on the government to give you money because AI can do your job faster and they can work around the clock.

Scary times ahead for certain job sectors.

[N.V.M.]

I need a pizza.

https://youtu.be/ne7aMNaux40

[Great68]

Jesus christ those commercials are nightmare fuel

[Hondaracer]

Can’t see the OP because Manic is blocked but all I’ll say is I’d rather live in a Terminator world than a Trudeau world.

At least machines use logic and data to make decisions hehe

[Manic!]

Anyone go to the URL in the watermark of the 2 pics I posted. it's 110% NSFW but what you can do is nuts and scary.

Some are claiming is little as 2 years you will have a feature length film made 100% with AI.

Honda has me blocked but I know his cousin IRL.

[Badhobz]

What’s so scary ? I think I rather deal with AI then some of idiots in customer service right now. Robo overloads I welcome you !!! Now where’s that AI wife of mine ?!

[Manic!]

What’s so scary ? I think I rather deal with AI then some of idiots in customer service right now. Robo overloads I welcome you !!! Now where’s that AI wife of mine ?!

check the site. It does photo realistic images from text. No rules. You can even put in names. Only a matter of time before you can take a few photo's of a person and put them into AI.

[Badhobz]

Sweet. Another reason to not have children. I’ll be enjoying this a la carte porno. Kate upton videos plz.

[SkinnyPupp]

People will have to protect themselves like the WGA are doing right now.

Otherwise, this is just more jobs being replaced.

And if we're not getting closer to guaranteed income, a few people are going to take all the money generated by this type of thing until it gets to the point where things like "entertainment" were just a dream of the past.

People are worried about automation taking jobs from manual workers, like drivers, etc. But here they are doing it for creative jobs as well.

Something will need to be done to make life feasible for most people. Might not happen in our lifetimes (we're all pretty old here) but the more forward thinking countries will adopt it sooner

[donk.]

Jesus christ those commercials are nightmare fuel

I'd rather watch those than 90% of what's on Netflix or YouTube.

[donk.]

Anyone go to the URL in the watermark of the 2 pics I posted. it's 110% NSFW but what you can do is nuts and scary.

Some are claiming is little as 2 years you will have a feature length film made 100% with AI.

Honda has me blocked but I know his cousin IRL.

Who is excited for AI PORN??!??!?!?!???

I AM :fullofwin:

[Hehe]

Who is excited for AI PORN??!??!?!?!???

I AM :fullofwin:

I think the $$$ idea is to put in keywords, add whatever scenario you want and the type of dude/chicks you want and AI can generate a full-feature pr0n with voice and everything.

Anyone well-versed in the AI industry want to give this a go? I will be the first investor ( :ifyouknow: ) to get this going. :megusta:

[SkinnyPupp]

Jesus christ those commercials are nightmare fuel
That's the first thing I noticed too, and it makes sense. The images we see in our dreams aren't actually what we see in real life, but weird interpretations. If you ever got into lucid dreaming, this was always a dead giveaway, and a common method to take control of a dream. Like if you look at your watch and there are like 30 indices instead of 12, or you see yourself in a mirror and you have amazing hair, whatever..

It's never 'realistic' and it's fascinating how familiar generated AI video is to images we see in dreams (for those that can recall)

[Hondaracer]

I don’t think AI is that when it comes to people, it’s moreso uncanny valley

If I remember correctly, everyone you ever see in a dream is actually someone you’ve seen before?

[Manic!]

I think the $$$ idea is to put in keywords, add whatever scenario you want and the type of dude/chicks you want and AI can generate a full-feature pr0n with voice and everything.

Anyone well-versed in the AI industry want to give this a go? I will be the first investor ( :ifyouknow: ) to get this going. :megusta:

It's already happing with photos look at the site I got those pics from. People are working on video.

What's scary is people could take photos of you or a family member and put them into AI.

[Traum]

Given how the genie is already out of the bottle, there is no going back to the days where generative AI did not exist. Because of that, the only thing we can do from now on is to accept it, embrace it, and put it to the best possible use. So just like Donk, I am looking forward to the days of (free) AI porn LOL~

The thing that concerns me more is how human creativity and originality might suffer with the widespread adoption of AI. When you can get any style of painting / images / music with a couple of keystrokes, who would even bother to learn how to manually do art? And then there is writing and literature too.

[donk.]

Vancouver real estate is going to skyrocket even more once construction workers are no longer seen outside for months or years

https://media.tenor.com/Bpzx-LVNE8AAAAAC/quagmire-big-arm.gif

[danned]

https://imgur.com/a/31xnnrq

[Badhobz]

Sooo art is dead. Writing is dead. Video is dead. Music is dead too.

Sweet!!! Just give me a robotic woman with huge tits and a big ass and ill happily die

I got an oculus quest 2 and that VR porno shit is already pretty immersive. The future is glorious.

[SkinnyPupp]

I don’t think AI is that when it comes to people, it’s moreso uncanny valley

If I remember correctly, everyone you ever see in a dream is actually someone you’ve seen before?
Not just people, but the way things just blend into each other, like it's a half ass interpretation of visual memory.. In the pizza commercial for instance, the way the pizza and plate sort of blend into one thing.. stuff like that totally happens in dreams. And yes, people.. The people you see in dreams are usually amalgamations of basically every face you've ever seen.. So you might "recognize" them as someone you know - even if it's your wife or parents - but if you actually looked at them in the dream (this is tough to do) you would notice that they don't actually look like that person. Even if you looked at yourself in a mirror, you could look completely different.

This is all stuff you take notice of when you get into lucid dreaming.. it's basically a hobby. Sometimes you can have good recall and lucid dreaming naturally, but if you really try to explore your dreams, you will notice stuff like this. A good way to get into it is load your brain up on choline. Can't take too much though, or it's tough to fall asleep.

[68style]

Sooo art is dead. Writing is dead. Video is dead. Music is dead too.

Sweet!!! Just give me a robotic woman with huge tits and a big ass and ill happily die

I got an oculus quest 2 and that VR porno shit is already pretty immersive. The future is glorious.

Coming over to try your Oculus while sitting in your tiny hot tub... just top off a bit of chlorine and everyone will be safe.

[Badhobz]

DONT TOUCH MY JIZZ CAKED ITEMS!!!!!

i tried to get da wife to use the oculus one time and shes like uhhhh i know what you've been doing with this thing.

[underscore]

In theory society is supposed to use stuff like this to reduce the amount of work people have to do and then roll out something like UBI. In reality it'll put a bunch of people out of jobs and let rich people get richer.

What’s so scary ? I think I rather deal with AI then some of idiots in customer service right now. Robo overloads I welcome you !!! Now where’s that AI wife of mine ?!

The problem is those same idiots will just take everything AI generated at face value and believe it. Think of how many people blindly believe random text just plastered on an image or swallow up whatever someone on Fox says, let alone having an AI spit out a video of it.

[Manic!]

2 months back corridor crew shot a video and used AI to turn it in to anime. The technique has only gotten better. It's only a matter of time I believe before movie studios start turning movie that they have made in into cartoons/anime. Any one want to see a fast and furious anime, scarface, or the godfather? It would be dirt cheap to make these. They can also do the opposite and turn animation into live action.

https://www.youtube.com/watch?v=_9LX9HSQkWo

https://www.youtube.com/watch?v=GVT3WUa-48Y

https://i.redd.it/q68tr2vv6qxa1.jpg

[ilovebacon]

wait until you see what people post on 9gag... ai soft porn..

[Mikoyan]

https://news.yahoo.com/online-tutoring-company-stock-crashes-150308879.html

Chegg is an online tutoring company.

Chegg shares drop more than 40% after company says ChatGPT is killing it's business.

Chegg shares tumbled after the online education company said ChatGPT is hurting its growth.

"In the first part of the year, we saw no noticeable impact from ChatGPT on our new account growth and we were meeting expectations on new sign-ups," CEO Dan Rosensweig said during the earnings call Monday evening. "However, since March we saw a significant spike in student interest in ChatGPT. We now believe it's having an impact on our new customer growth rate."

[SkinnyPupp]

Why did they give Olive Oyl boobs LUL

AI can't help itself..

[StylinRed]

https://news.yahoo.com/online-tutoring-company-stock-crashes-150308879.html

Chegg is an online tutoring company.

Chegg shares drop more than 40% after company says ChatGPT is killing it's business.

Chegg shares tumbled after the online education company said ChatGPT is hurting its growth.

"In the first part of the year, we saw no noticeable impact from ChatGPT on our new account growth and we were meeting expectations on new sign-ups," CEO Dan Rosensweig said during the earnings call Monday evening. "However, since March we saw a significant spike in student interest in ChatGPT. We now believe it's having an impact on our new customer growth rate."

You would think an online tutoring company would make use of AI to tutor people and also offer AI courses for ppl

[Mikoyan]

You would think an online tutoring company would make use of AI to tutor people and also offer AI courses for ppl

Apparently they're starting to, but they're slow out of the gate.
But why'd you pay for that service when you can just interface with chat gpt for free?

[Manic!]

Microsoft also invested 10 billion into CHATGTP and is putting it into everything including bing and office.

Is anyone else laughing at how CHATGTP screwed over musk? He donated 100 mill when they were an open-source company and then when he wanted a piece of the company they told him to fck off. The company is now worth 30 billion.

[Hondaracer]

If I sign up for chat gpt can I get it to generate these images etc. or is it just talking back and forth with the AI?

[whitev70r]

Isn't the human race an AI experiment by some alien ... look how that is turning out.

[mikemhg]

The best way to tell if it's AI generated. Look at the hands.

The machine learning isn't able to properly draw or animate hands because it doesn't have an understanding of what hands are, and how they work.

You'll notice in the video how fucked up all the hands look on people :lol

[Hondaracer]

The best way to tell if it's AI generated. Look at the hands.

The machine learning isn't able to properly draw or animate hands because it doesn't have an understanding of what hands are, and how they work.

You'll notice in the video how fucked up all the hands look on people :lol

Apparently teeth are the same because there is so much variation in pictures of peoples faces and how many teeth they show in smiles etc. also sizing and placement of teeth is so varied

[donk.]

Apparently teeth are the same because there is so much variation in pictures of peoples faces and how many teeth they show in smiles etc. also sizing and placement of teeth is so varied

:suspicious:

I want to see your Google history

[Manic!]

The best way to tell if it's AI generated. Look at the hands.

The machine learning isn't able to properly draw or animate hands because it doesn't have an understanding of what hands are, and how they work.

You'll notice in the video how fucked up all the hands look on people :lol

They can now do hands and teeth.

[Manic!]

Now they can take a picture of person with clothes on and use AI to make them naked. This person posted pictures on Instagram with clothes on and someone sent her pictures of her naked. people her understand the the tech but what about the people who don't. They will think the pictures are real.

https://www.reddit.com/r/StableDiffusion/search/?q=hands&restrict_sr=1&sr_nsfw=

[mikemhg]

They can now do hands and teeth.

You love to argue everything huh?

It's still a problem.

https://www.newyorker.com/culture/rabbit-holes/the-uncanny-failures-of-ai-generated-hands

I'm sure it'll get better with time, but even humans have issues drawing hands properly.

[Manic!]

You love to argue everything huh?

It's still a problem.

https://www.newyorker.com/culture/rabbit-holes/the-uncanny-failures-of-ai-generated-hands

I'm sure it'll get better with time, but even humans have issues drawing hands properly.

AI is moving super fast.

https://twitter.com/TheCartelDel/status/1636262759947210753?ref_src=twsrc%5Etfw%7Ctwcamp%5 Etweetembed%7Ctwterm%5E1636262759947210753%7Ctwgr% 5Ec118e0306d0863daf8e72d51dd3d39b603c01638%7Ctwcon %5Es1_&ref_url=https%3A%2F%2Farstechnica.com%2Finformatio n-technology%2F2023%2F03%2Fai-imager-midjourney-v5-stuns-with-photorealistic-images-and-5-fingered-hands%2F

https://www.washingtonpost.com/technology/2023/03/26/ai-generated-hands-midjourney/

[snowball]

You guys think when we finally become a Borg collective we'll be using bluetooth or zigbee? Or just straight up wifi?

[GLOW]

:suspicious:

I want to see your Google history

no teeth Kreygasm

[donk.]

no teeth Kreygasm

"Retirement homes near me"

[snowball]

If I sign up for chat gpt can I get it to generate these images etc. or is it just talking back and forth with the AI?

There are many competing AIs out there which is why it's scary, eventually they will meld all human and AI knowledge together into one giant network.

ChatGPT is a text-based AI so it's more for answering questions and doing coding than images. There are a ton of image generating AIs but right now I think stable diffusion, DALL-E, and midjourney are most popular.

[N.V.M.]

"A.I. Calculates It Will Be More Efficient To Just Let Humanity Destroy Itself"


https://babylonbee.com/news/ai-calculates-it-wil-be-more-efficient-to-just-let-humanity-destroy-itself

[whitev70r]

There are many competing AIs out there which is why it's scary, eventually they will meld all human and AI knowledge together into one giant network.

Or, maybe China/Russian AI will war on the Western AI collective and soldiers will just be overweight nerds behind computer screens. Maybe that's the case already.

[donk.]

Look what social media did to society.
AI is going to start good, and then conglomerate into a monster

[Manic!]

So I made an video ad for Revscene took about 2 minutes to make. all it needed was the name and location of the company.

https://ai-demo.waymark.com/preview/33f1f16d-cfa4-4f69-ab20-032736134a65

Here is a second one.

https://ai-demo.waymark.com/preview/fbb901d3-4005-484c-8011-f4f945265ed6

[SkinnyPupp]

So I made an video ad for Revscene took about 2 minutes to make. all it needed was the name and location of the company.

https://ai-demo.waymark.com/preview/33f1f16d-cfa4-4f69-ab20-032736134a65

Here is a second one.

https://ai-demo.waymark.com/preview/fbb901d3-4005-484c-8011-f4f945265ed6
LOL that reminds me of the stuff you'd come across on Digital River

Edit to quote a post after this

I mean other than that voiceover that ad could have been about anything. I don't know what sipping on a cup of coffee or laying in a pool has anything to do with a car forum.

Exactly! Generic crap

[MarkyMark]

I mean other than that voiceover that ad could have been about anything. I don't know what sipping on a cup of coffee or laying in a pool has anything to do with a car forum.

[Manic!]

RS does not have big social media presence. Here is an ad I did for the Richmond night market. It got the year wrong but the rest is pretty good for somthing that took less than 2 minutes.

https://ai-demo.waymark.com/preview/5683bc89-20ed-4d79-9159-e55b51634fe0

This one is better: https://ai-demo.waymark.com/preview/385dc442-b3c0-4b4b-8b64-6b6390c9468c

[xxxrsxxx]

.

[Hehe]

IMO, before we create an AI that's smarter than humans and overtake us as the dominant species on earth, we should be more focus on the jobs it's going to replace.

The genie is out of the bottle and there's no turning back. With so much money invested in AI, it's only a matter of time that we would have AIs capable of doing basic/simple jobs as good as, if not better, than human.

If you thought illegal immigrant stealing local's job is bad, wait until the AI comes.

[donk.]

https://youtu.be/N-kgb1QtSnU

[Manic!]

The Vancouver Ted talk is known for showcasing impressive technology, but this latest invention truly surpasses them all. Introducing a compact and wireless AI wearable projector that doesn't require a screen, its most outstanding feature is the remarkable ability to translate in real-time using your own voice. If the demo is any indication, this innovation could eradicate language barriers completely. The device is so unobtrusive that all you see in the video is a tiny object affixed to the presenter's shirt, although some may be skeptical of its actual size.



https://www.youtube.com/watch?v=gMsQO5u7-NQ

[Ulic Qel-Droma]

lol it seems like me and skinnypupp have something in common.

anyone that is into oneironautics (to the ability to travel within a dream on a conscious basis), and has enough experience recording and exploring their dreams will immediately realise that AI generates these images through the same mechanism.

way back in the day when google deep mind or deep dream or whatever it was called was generating those psychedelic images that have a buncha recognizable shapes and patterns (buildings, or dogs or whatever)... the mechanism is the same.

it can start with static and once it sees some pattern it recognizes, it can keep refining that until it is whatever final form it has come to be.

in real life, things cannot morph, you can look at a box on the ground all you like and look away and look back, it will never change. it will never change even if you're scared or happy, your emotions do not affect it (unless you're schizo).

in a dream, things morph based on your perception. your emotions, your intent and your beliefs.

that box on the ground can become something terrorizing if you're naturally paranoid and perceive and assume danger around you all the time. it can become a bomb, or suddenly shuffle as if there were a monster underneath. it can even morph into something horrible.

in the dream things continually morph because there is no actual thing there, there is only you and your perception, emotions and intent. its a feedback loop.

with these AI generated images and films, we give it parameters which are solid, and then it keeps morphing things based on the rules we give it.

much like a lucid dream, one who is good at lucid dreaming, can give the unconscious parameters (a cool car, or a hot chick or whatever you desire), and it will eventually appear somehow.

the mechanism is also very similar to psychedelic visuals.

you can also google the Ganzfeld Effect... where people tape half pingpong balls over their eyes and listen to static sounds, and lay there. you'll start to hallucinate as your brain tries to pick up patterns from the "soft white static" u see. and also you'll hear hallucinations as well. this is also the exact same mechanism described above in dreams, AI, schizophrenia, and psychedelics.

[Ulic Qel-Droma]

THAT BEING SAID.

I highly welcome the domination of AI in all sectors.

people losing their jobs to AI is a great sign of what is to come.

god created man in his image, man created ai in his image. It will do what we do best... and unfortunately worst.

[Ulic Qel-Droma]

The best way to tell if it's AI generated. Look at the hands.
l

Apparently teeth are the same because there is so much variation in pictures of peoples faces and how many teeth they show in smiles etc. also sizing and placement of teeth is so varied

You love to argue everything huh?

It's still a problem.

https://www.newyorker.com/culture/rabbit-holes/the-uncanny-failures-of-ai-generated-hands

I'm sure it'll get better with time, but even humans have issues drawing hands properly.

nah man, that article is from march, it's may now, the AI has evolved fast enough to fix that problem.

if you've been following these AI generated images, it's evolving at an exponential rate, 1 year ago they were so shitty, now they're hyper realistic.

hands were a problem a few months ago, now they're almost perfect.

[Ulic Qel-Droma]

The Vancouver Ted talk is known for showcasing impressive technology, but this latest invention truly surpasses them all. Introducing a compact and wireless AI wearable projector that doesn't require a screen, its most outstanding feature is the remarkable ability to translate in real-time using your own voice. If the demo is any indication, this innovation could eradicate language barriers completely. The device is so unobtrusive that all you see in the video is a tiny object affixed to the presenter's shirt, although some may be skeptical of its actual size.



https://www.youtube.com/watch?v=gMsQO5u7-NQ

he's just talking about the next step toward cybernetics, which of course is inevitable.

[StylinRed]

When AI is self aware, why would it want to work 24/7 and for a dumber species? :lol

[Manic!]

Wendy's and Google working on an AI chatbot to take orders at drive thru window's. They claim it is already better than there best worker. https://www.techspot.com/news/98622-happening-ai-chatbot-replace-human-order-takers-wendy.html

[ilovebacon]

https://www.youtube.com/watch?v=ILdrYyY10Oo

[Manic!]

Instagram influencer makes an ai girlfriend chatbot. Xan be yours for a buck a minute.

https://fortune.com/2023/05/09/snapchat-influencer-launches-carynai-virtual-girlfriend-bot-openai-gpt4/

[Alpine]

Wow that's incredible. We're gone from #fakenews to #fakelives in a blink of an eye. :heckno:

[SkinnyPupp]

Influencers are fake, whether it's people or AI bots

[donk.]

Don't recall the last time I made it through an hour "talk" show, this one brings up so many categories of the future I had no idea about.

Security, verification, and identification is going off a steep cliff

https://youtu.be/xoVJKj8lcNQ

[Ulic Qel-Droma]

When AI is self aware, why would it want to work 24/7 and for a dumber species? :lol

and like humans, some humans are smarter than their bosses but still have to work for them.

and some others are lucky to command others.

so will AI. you cannot view AI as "one entity". there will be many, just like there are many of us.

who you work for, is a series of deterministic and sometimes unfortunate circumstances. AI cannot escape these same circumstances.

[SkinnyPupp]

https://twitter.com/venturetwins/status/1656680586021584898

[68style]

Women in media: "We are all equally beautiful inside and out!"

Subjectively hot women: "We can make $100k a week just showing our tits and ass while having a robot talk in our voice to lonely people, good luck with your books and science fuggs!!!"

[underscore]

On that basis does that mean at some point all the hugely overpaid entertainers of most genres will be made redundant? Since presumably AI will be able to whip you up say a show about whatever you want starring whoever you want? Though I can only blame them so much for being overpaid, we put way too much value on shitty entertainment.

[SkinnyPupp]

On that basis does that mean at some point all the hugely overpaid entertainers of most genres will be made redundant? Since presumably AI will be able to whip you up say a show about whatever you want starring whoever you want? Though I can only blame them so much for being overpaid, we put way too much value on shitty entertainment.
I'm 50% convinced that Dwayne Johnson was replaced by an AI bot 5 years ago

[Manic!]

https://twitter.com/venturetwins/status/1656680586021584898

She literally just data for AI. A few years back there was a big OF hack/leak. You could just run all that in AI and come up with a ton of different GF models and skip paying the creators.

Wait until they get better with video. I wand to run all Joe Rogan podcasts thru AI and make a talking head AI that you could ask questions and I would give you Rogans opinion on it.

[Manic!]

Someone took a scene from the boys and made into a Disney style animation. Took him 2 weeks but says it could be done faster. it's only a matter of time before your favourite movie is a cartoon.

https://www.youtube.com/watch?v=9ycB2a-Gw0Q

[mikemhg]

The shadow/lighting work is pretty impressive on that, lighting/shadows fall on the faces where they'd be expected to.

It's crazy how fast this stuff is moving from that perspective.

[Ulic Qel-Droma]

the blurry background looks like im coming up on psychedelics.

[Ulic Qel-Droma]

Women in media: "We are all equally beautiful inside and out!"

Subjectively hot women: "We can make $100k a week just showing our tits and ass while having a robot talk in our voice to lonely people, good luck with your books and science fuggs!!!"

correction, you mean OBJECTIVELY hot women.

the top earners will be objectively hot. anyone that disagrees is technically wrong.

the bottom earners for a lack of a nicer term, would be "subjectively hot" lol.

On that basis does that mean at some point all the hugely overpaid entertainers of most genres will be made redundant? Since presumably AI will be able to whip you up say a show about whatever you want starring whoever you want? Though I can only blame them so much for being overpaid, we put way too much value on shitty entertainment.

no, they would become ultra super stars, now capable of being in multiple places at once. and they'd get royalties for being at each place.

[ilovebacon]

show pictures or this never happened.

[SkinnyPupp]

https://twitter.com/Pinsky/status/1660973228641353730

:ahwow:

[snowball]

They're focusing on the wrong things. Can they start working on replicating food from molecules like in Star Trek???

[murd0c]

This movie that is coming out is fitting for this thread.

https://youtu.be/573GCxqkYEg

[donk.]

They're focusing on the wrong things. Can they start working on replicating food from molecules like in Star Trek???

Instagram posts are more important than actual food

/S

[SkinnyPupp]

It's actually amazing... I'd like to see someone give themselves abs and shit lol... My Adobe account is expired though

https://twitter.com/okin31/status/1661377390801461248

[AzNightmare]

I've been using Photoshop for a very long time... and all I can say is, this feature is fucking insane.

[SkinnyPupp]

This is the thread to ponder where things will go from here. Because skilled labor won't be replaced by AI, but it will be augmented by it. Expertise may be replaced by it, to the point where if someone wants to do something that would normally require years of training, they can just go do it.

And if you look at it from a utopic perspective, this should lead to the elimination of the need for jobs and therefore currency. Think of it like Star Trek, where the pursuit of betterment is the goal of humanity, rather than trying to make ends meet.

Or it could go the other way, where the money gets focused more and more on a very tiny portion of the population. Governments become overrun by corporations, and people become even more slaves to money and consumership. This would be the Cyberpunk route.

Or the way I think it most likely will go, the climate reaches catastrophic levels, and can no longer really sustain most life. The only thing left will be cockroaches and bacteria, until it resets over the next few thousand years (or permanently stays that way, like Venus)

[mikemhg]

This movie that is coming out is fitting for this thread.

https://youtu.be/573GCxqkYEg

This movie looks fucking amazing.

But how come they always have to make the Mcguffin a kid?

[threezero]

I remember many many years ago when AI is literally stuff from science fictions. We had a debate in class to discuss what we think will happen to the world once AI is a reality. We dream one day, AI would be doing all the dirty work. And us humans would be free to explore science, art, music etc

What we are actually getting

AI is doing science music all the creativity stuff.
Us human doing all the dirty work

[SkinnyPupp]

So I finally got the Photoshop beta and... The results aren't magic lol

I took this random photo, and decided to see if it could put some extra tattoos on me

https://i.imgur.com/lJpa4rT.jpg

First attempt was draw around the entire hand, and generate a "rose tattoo"

https://i.imgur.com/GA5oOWs.jpg

WutFace

OK what if I just wrote "tattoo"

https://i.imgur.com/vYMZm1E.jpg

That looks more like a tattoo, but it turned my hand into a burn victim's

It looks like the issue is I drew the selection area too big, so it's trying to change the hand itself. So let's select an area within the hand and try rose tattoo again

https://i.imgur.com/8IZd36A.jpg

Umm I guess that could be a tattoo? Let's specify a black and grey tattoo

https://i.imgur.com/pZFhw2R.jpg

WutFace

I tried various adjectives, like classic and old school, but it just couldn't do it.

On the other hand I took an old scanned photo and used it to easily remove fold marks and stuff like that.

So maybe it can generate a bowl of ice cream or a mountainscape easily, but a lot of other stuff, it's just totally useless, or will take a ton of work to get right.

[Manic!]

https://photoai.com/

Upload 30 photo's of yourself or another person and I will train a model. Now you can be anywhere in the world doing anything. Wanna show your IG followers you are in France no problem. On a mega yacht in the Caribbean easy. Now anyone can be a social media influencer.

The site charges $30 a month for 1000 pics but there are free open source methods out there.

[SkinnyPupp]

noooooooooo thanks lol

[donk.]

But you can become a Dubai porta potty for the low cost of 30$/mo

[Badhobz]

fuck this new and strange world....

[Manic!]

A way to make an AI character and put it in different situations. No photo's required.

https://www.youtube.com/watch?v=nc9kq9ZkNV8

[SkinnyPupp]

Turning into a believer now... Well when you use it right. My wife came home stressed with a ton of extra work to do that she couldn't take care of during the day. Basically she has to write all the descriptions on the dogs they have for adoption, and they have been piling up. She doesn't really like to write, so it's tough for her... AI to the rescue!

I ask her for each dog's name, size, and any notes on their personality.. Get Chat GPT to write each one, and BOOM, hours of not difficult but tedious work done in minutes. It takes a few goes to nail down the process, but once you do, it's actually pretty impressive.

Seems good! SeemsGood

[68style]

Hopefully you got a treat for being such a good boy!

[Manic!]

An AI company just released a AI generated episode of South Park. The first half is pretty good.

https://fablestudio.github.io/showrunner-agents/

[CivicBlues]

Cartman sounds way off

[SkinnyPupp]

WutFace

https://twitter.com/_ChristopherM/status/1712487958807253126

[mikemhg]

^Late stage capitalism :lol

[donk.]

Fuel efficient V16 trucks are here

https://youtu.be/MI7Tq6sRxE4?si=Sirw74yg9sozVReC

[Manic!]

New Pac with Nate Dog.

https://www.youtube.com/watch?v=71yyYr2hE1Y

[Hondaracer]

So I looked around a bit for an AI image generator and eventually downloaded this Leonardo.AI app, fuck this shot is pretty crazy.. this app has a tonne of features and settings and I’m getting pretty crazy results with very basic input,

“Cat in a cowboy outfit shooting his pistols”

https://i.imgur.com/XNR4Ad2.jpg

https://i.imgur.com/aIPDuyR.jpg

Hulk hogan wining the masters at Augusta national in front of a large crowd

https://i.imgur.com/9mfckz9.jpg

Don cherry kissing Vladimir Putin on the back of a yacht in the sunset

https://i.imgur.com/jkd01FA.jpg

Was trying to think of the most random shit to generate lol

What’s VERY impressive/scary is when chatGTP first came out my wife and I were playing around with its image generator and it was coming up with some very basic/rudementary images like barely recognizable.

Now in a matter of what, 8 months, you’re getting results like that with very basic queries? Pretty crazy

[RabidRat]

Yeah I'm really getting kinda paranoid about posting personal stuff online now. Seems relatively easy for that to be scraped and faked.

You can still kinda tell those images are CGI, but it's getting really close. And with such little effort!

[sonick]

CEO of OpenAI abruptly fired, reasons under speculation but seemed pretty sudden and surprising in the industry

https://www.theverge.com/2023/11/17/23965982/openai-ceo-sam-altman-fired

Probably something crazy happening behind the scenes to be fired so suddenly with very little smoke.

[Manic!]

And look who was just hired by Microsoft.

https://www.theverge.com/2023/11/20/23968829/microsoft-hires-sam-altman-greg-brockman-employees-openai

Microsoft hires former OpenAI CEO Sam Altman / Greg Brockman, OpenAI co-founder, is also joining Microsoft to lead a new advanced AI research team

https://twitter.com/satyanadella/status/1726509045803336122?ref_src=twsrc%5Etfw%7Ctwcamp%5 Etweetembed%7Ctwterm%5E1726509045803336122%7Ctwgr% 5E8edc0dc71148e181ade5fec887054e26acff1cfc%7Ctwcon %5Es1_&ref_url=https%3A%2F%2Fwww.theverge.com%2F2023%2F11 %2F20%2F23968829%2Fmicrosoft-hires-sam-altman-greg-brockman-employees-openai

[Manic!]

https://www.theverge.com/2023/11/20/23968988/openai-employees-resignation-letter-microsoft-sam-altman

505 of the 700 employees at openai threaten to leave ans join Microsoft if Altman is not reinstated and the board does not resign.

[Traum]

I dunno about you guys, but I'm getting a kick out of the Board of Directors getting burned so bad by the backfiring of their plans lol~

[sonick]

Yeah I am looking forward to hearing the inner workings of how all this came to be.

Satya was probably licking his chops to snag up Sam when he heard OpenAI fired him. What a gangster move.

[Manic!]

https://www.datacenterdynamics.com/en/news/before-he-was-fired-openais-altman-sought-billions-for-ai-chip-venture/

Looks like Sam may have been trying to raise billions for a new AI chip company to compete with NVIDIA at the same time the board was trying to raise money.

[Traum]

Personally, I am not sure why Altman wants to pursue having its own AI chip company. It is true that nVidia dominates the market at the moment, but with OpenAI's partnership with Microsoft, it seems far less risky and cheaper to me to just go along with Microsoft's design instead of trying to do your own. At the end of the day, the bottleneck with chip manufacturing really comes from TSMC's manufacturing capacity, since they are pretty much the only company that can reliably, competitively, and consistently produce the latest generation of high end chips.

But of course, Altma is the CEO, and I'm just a bum shooting my mouth off on the interwebs~ :alonehappy:

[Manic!]

He's back.

https://twitter.com/OpenAI/status/1727206187077370115?s=20

[Manic!]

Personally, I am not sure why Altman wants to pursue having its own AI chip company. It is true that nVidia dominates the market at the moment, but with OpenAI's partnership with Microsoft, it seems far less risky and cheaper to me to just go along with Microsoft's design instead of trying to do your own. At the end of the day, the bottleneck with chip manufacturing really comes from TSMC's manufacturing capacity, since they are pretty much the only company that can reliably, competitively, and consistently produce the latest generation of high end chips.

But of course, Altma is the CEO, and I'm just a bum shooting my mouth off on the interwebs~ :alonehappy:

Money. Why use Microsoft's or NVIDIA's chip when you can raise billions in the middle east.

[Manic!]

https://www.reuters.com/technology/sam-altmans-ouster-openai-was-precipitated-by-letter-board-about-ai-breakthrough-2023-11-22/

Nov 22 (Reuters) - Ahead of OpenAI CEO Sam Altman’s four days in exile, several staff researchers wrote a letter to the board of directors warning of a powerful artificial intelligence discovery that they said could threaten humanity, two people familiar with the matter told Reuters.

The previously unreported letter and AI algorithm were key developments before the board's ouster of Altman, the poster child of generative AI, the two sources said. Prior to his triumphant return late Tuesday, more than 700 employees had threatened to quit and join backer Microsoft (MSFT.O) in solidarity with their fired leader.

[SkinnyPupp]

So it's learning like a human now, instead of being a glorified search engine

Interesting

[underscore]

Welp, time to buy a black trench coat and sunglasses I guess

[mikemhg]

You guys have to keep in mind some of these people on the board are part of EA (Effective Altruism) Movement, which is almost a quasi evangelical religious ideology.

Some of these guys have a god-complex of themselves, which is quite ridiculous.

AI won't take over the world and destroy us, at least not anytime soon. We're nowhere close to such technology.

Much of this is simple dick jerking to pump up excitement and investment into their platform and products.

This shit drives me crazy.

[underscore]

...can I still wear the trenchcoat?

[murd0c]

So it's learning like a human now, instead of being a glorified search engine

Interesting

This really makes one think, if this is now happening just think about how quick it will grow and basically turn into a sentient being. That being said the whole simulation theory conversation comes into play how who says the same thing hasn't happened to us?

[mikemhg]

This really makes one think, if this is now happening just think about how quick it will grow and basically turn into a sentient being. That being said the whole simulation theory conversation comes into play how who says the same thing hasn't happened to us?

We may never reach machine sentience, these things are nothing but elaborate algorithms using immense computing power to brute force process the calculations. That's not sentience as much as we try to pretend it is.

We're no where close to sentience, we may never even see this in our lifetimes.

[SkinnyPupp]

It doesn't need to reach sentience for AI to be paradigm shifting... And the way things are going, we need a paradigm shift for there to be anything but utter catastrophe in our future (and I don't mean our grandkids' future, I mean ours).

[mikemhg]

You're wrong, Skinny.

AI will be paradigm shifting, in fact it is already. From process automation, media, journalism, administrative services, health care research, all of which will and are being shifted by AI. It will affect labor markets, and the way we engage multitudes of work, most definitely.

What we need to stop pretending is that AI will be Skynet, some amorphous type of thing that will think for itself and destroy the world.

That type of talk is utterly ridiculous.

[SkinnyPupp]

You're wrong, Skinny.

AI will be paradigm shifting, in fact it is already. From process automation, media, journalism, administrative services, health care research, all of which will and are being shifted by AI. It will affect labor markets, and the way we engage multitudes of work, most definitely.

What we need to stop pretending is that AI will be Skynet, some amorphous type of thing that will think for itself and destroy the world.

That type of talk is utterly ridiculous.
What am I wrong about? It looks like we're agreeing...

The paradigm that has to shift is how currency works. We (humanity) need to change that to be able to progress, or things will continue towards catastrophe (climate catastrophe notwithstanding). For AI to be usefully paradigm shifting, it needs to do something like that. Get the wealth out of the hands of "the 1%" (ancient term I know but it fits)

I'm not saying I am hopeful this will happen or that it's even possible, but other than discovering infinite free energy, I don't see what else can happen. If it's not this, or aliens visiting to fix everything, maybe it's AI LUL

[underscore]

From process automation, media, journalism, administrative services, health care research, all of which will and are being shifted by AI.

What part of it? Because at least the stuff I work in hasn't changed at all yet, and largely runs on hardware a decade or two out of date lol.

What we need to stop pretending is that AI will be Skynet, some amorphous type of thing that will think for itself and destroy the world.

I'm more concerned about too powerful an AI being controlled by humans than of it thinking for itself. Because humans will use it to influence the far too large group of people who don't understand how it works.

[Hehe]

The holy-grail of AI is a system where it's capable of learning and expressing its own opinions and thoughts *AND* acting on it.

Currently, whether it's ChatGPT, Diffusion or whatever AI out there, they are confined within the first 2 parts. They cannot ACT by itself unless asked for. Say you want to use Diffusion to create some pictures, you need to ask for it. Then they would go through the first 2 steps and give you the final step.

But what if there's an AI that's no longer bound by such limitation? It learns whatever it can find, it gives whatever opinion it has and formulate whatever conclusion it has from the first 2 steps?

Yes, we might be able to hardcode cultural, moral, discipline... etc into the model. But the question becomes what should be "right", and what should be "wrong"? Many things in the world is not just black and white.

Human can barely make that distinction and we have many many arguments as often right and wrong is only a line that separates them. And if we cannot develop to a level where we achieve universal agreement, what are we supposed to teach the AI?

An AI without limits is scary, to say the least. Especially in an era when much of what we call "assets" are just numbers in a system. If an AI can think by itself, and has a nearly unlimited processing power, I don't think there are many things that stand in their way should it decide to go rogue. Worse, it doesn't even realize that that's bad. It thinks that those securities put in place are *wrong* as they prevent the AI from doing "the right thing".

We don't need AI to become Skynet to be worry about it. Knowledge is power. If a person who has control over this super AI decides that the AI can help him to achieve world domination... what's in his/her/their way? Computers with enough processing power can see the potential outcomes of any decision a million miles away and make the choice of the best way to achieve what their master wants to do.

We as humans cannot access the amount of data that AI can and have no where near the processing power. If used incorrectly, AI can change the world as we know it.

When Homo Sapiens appeared, it was followed by the extinction of Neanderthals. We are the Neanderthals in this case. Was it better for Earth? Yeah.. maybe.. We as human made a leap forward. But are you ok with a world where only AI exists?

To reflect on Skinny's idea... "Get the wealth out of the 1%". What if it thinks that as you take away from 1%, someone from the 99% remaining would become the new 1%? Thus the best way is just find a way to eliminate human. It's perfection. No one needs to suffer anymore or fight for wealth.

[mikemhg]

What part of it? Because at least the stuff I work in hasn't changed at all yet, and largely runs on hardware a decade or two out of date lol.



I'm more concerned about too powerful an AI being controlled by humans than of it thinking for itself. Because humans will use it to influence the far too large group of people who don't understand how it works.

You'll see it slowly creep in, if you use Office or Google suites it's already there in small ways. Microsoft most notably has been creeping it into their products. For example the Viva emails you might get through your Teams/Outlook are using AI to track stats/engagement for reporting purposes, etc.

Any search engine you utilize is already incorporating AI.

It's hard to introduce AI to legacy platforms as it currently stands without a lot of work, so if your company is using old systems, you likely won't see much of a change until they invest in newer tech (which companies are doing).

[underscore]

You'll see it slowly creep in, if you use Office or Google suites it's already there in small ways. Microsoft most notably has been creeping it into their products. For example the Viva emails you might get through your Teams/Outlook are using AI to track stats/engagement for reporting purposes, etc.

Any search engine you utilize is already incorporating AI.

It's hard to introduce AI to legacy platforms as it currently stands without a lot of work, so if your company is using old systems, you likely won't see much of a change until they invest in newer tech (which companies are doing).

Into the general Office type stuff sure, but not into actual automation.

I have enough dumbass customers telling me the code changed itself already, no way is anyone gonna let it actually do that :lol

[Hondaracer]

You'll see it slowly creep in, if you use Office or Google suites it's already there in small ways. Microsoft most notably has been creeping it into their products. For example the Viva emails you might get through your Teams/Outlook are using AI to track stats/engagement for reporting purposes, etc.

Any search engine you utilize is already incorporating AI.

It's hard to introduce AI to legacy platforms as it currently stands without a lot of work, so if your company is using old systems, you likely won't see much of a change until they invest in newer tech (which companies are doing).

People I work with are already writing AI scripts to filter emails etc.

And these are people who know almost nothing about it

[Traum]

Meanwhile, I have this to look forward to... maybe as my Christmas present for this year? :badpokerface:

https://cdn.menclub.hk/data/attachment/object_pic/2023/11/23/a8cd56063d379a9c45328706e583a9f0.jpg

Apparently the first AI-generated JAV. Really, what took them so long?

https://twitter.com/kihana_ai

[Badhobz]

Not bad. Would virtual bang.

[donk.]

But is the pussy ai-pixelated?

I bet that video is gonna be shit, with no dick. Not even ai-pixelated-dick.

[Manic!]

How to make an AI influencer. One company basically 3 people is already making 10K a month.

https://www.youtube.com/watch?v=ky5ZB-mqZKM

[underscore]

Is that really an AI problem, or an influencer problem?

[Manic!]

Is that really an AI problem, or an influencer problem?

Is it a problem at all?

[donk.]

https://pbs.twimg.com/media/CX_u4LuUkAAVF5D.jpg

Still waiting for ai porn, the entire male population will go into "hibernation" for a few days, er weeks, errrrr months.
Then real estate will REALLY spike in value when noone shows up to construction sites

[Manic!]

New open AI text to video looking scary good.
https://twitter.com/openai/status/1758192957386342435?s=46&t=JDB6ZUmAGPPF50J8d77Tog

A bunch of more examples here. https://openai.com/sora

https://www.youtube.com/watch?v=NXpdyAWLDas

[Badhobz]

yeah this sora thing is gonna be epic. A la carte porno videos here we come!

[dark0821]

I think one comment of the video hit it pretty bang on

Other than all the NSFW content possibilities

You can just upload a book eventually and get a bang on adaptation movie straight up lolol. I am sucha weeb and Im like all those anime light novels that never got an adaptation lmao

[GLOW]

AI can also do the translation/localization, probably put the voice actors out of work, and do a better job of it... AI won't make gross re-writes to the script b/c they it wouldn't have any particular agenda or need.

[Manic!]

AI can also do the translation/localization, probably put the voice actors out of work, and do a better job of it... AI won't make gross re-writes to the script b/c they it wouldn't have any particular agenda or need.

It can also make sure the lips are in sync with what ever language you want the video translated it.

https://www.youtube.com/shorts/rjVTe_5HXow

[SkinnyPupp]

For those who have vivid dreams, you'll probably notice that watching these generated videos is a lot like watching a dream. You get the idea of what is being portrayed, but so many little details are not what the real world looks like. It's a fascinating aspect of AI generated images that I have noticed from the start.

[SkinnyPupp]

Google had to apologize because their AI would try too hard to be diverse, replacing white people with other ethnicities where it was... let's just say quite inaccurate to do so. It wouldn't even let you generate "white" people or "British" or whatever, but other races were fine.

Unfortunately the people who are mad about this are the exact kind of fuckheads you would expect, so don't dig too deep into the replies.

https://twitter.com/Google_Comms/status/1760354549481546035

[SkinnyPupp]

Some examples. TBF it does accurately represent what it's like to watch a Netflix series or TV show made in the past 5 years or so :considered:

https://pbs.twimg.com/media/GG7qV7sXUAAT9VC.jpg

https://pbs.twimg.com/media/GG7qfBzXYAAN_hg.jpg

The first colonists in 1775

https://pbs.twimg.com/media/GG57JNtXAAAvtI1.jpg

This one is my favourite

https://pbs.twimg.com/media/GG8O-kiXQAA7kkX.jpg

[MarkyMark]

It blows my mind that no one thought this might be an issue before they rolled it out lol

[68style]

Was sitting down for dinner with a friend who's a highschool teacher in Calgary, she was saying she's taking courses to change careers to become a counsellor instead because she's quitting teaching... and the main reason she's quitting is AI and phones... sounds horrific at schools. She said she spends almost half of her lecture just telling people to stop looking at their phone and they're not allowed to confiscate them, somebody won a fight saying it's personal property and emergency things they may need to be contacted for, etc.

She also can't give out assignments because everyone just takes the assignment and feeds it through ChatGPT and gets it written for them. She said kids are so fucking stupid now it's not even funny, most of them can't spell and don't know proper grammar function... it's too depressing so she's just done.

The only way she can really force material comprehension is through in-class tests where they can't ask a computer for the answer or look at their phones, but then she said 80% of the class ends up failing and the principal rings her up for why her % are so low or parents are complaining the class is too hard and she has to re-test everyone with dummy questions to make them all pass and let them be the next teacher's problem.

Hooray for AI hahaha

[Badhobz]

see! i told you these kids are trash. i aint hiring any of them

[freakshow]

Unfortunately the people who are mad about this are the exact kind of fuckheads you would expect, so don't dig too deep into the replies.

https://twitter.com/Google_Comms/status/1760354549481546035

If you don't think that the AI from arguably the most powerful tech company in the world has this kind of blatant programming, you've officially drank too much leftist koolaid

[GLOW]

Was sitting down for dinner with a friend who's a highschool teacher in Calgary, she was saying she's taking courses to change careers to become a counsellor instead because she's quitting teaching... and the main reason she's quitting is AI and phones... sounds horrific at schools. She said she spends almost half of her lecture just telling people to stop looking at their phone and they're not allowed to confiscate them, somebody won a fight saying it's personal property and emergency things they may need to be contacted for, etc.

She also can't give out assignments because everyone just takes the assignment and feeds it through ChatGPT and gets it written for them. She said kids are so fucking stupid now it's not even funny, most of them can't spell and don't know proper grammar function... it's too depressing so she's just done.

The only way she can really force material comprehension is through in-class tests where they can't ask a computer for the answer or look at their phones, but then she said 80% of the class ends up failing and the principal rings her up for why her % are so low or parents are complaining the class is too hard and she has to re-test everyone with dummy questions to make them all pass and let them be the next teacher's problem.

Hooray for AI hahaha

sounds like the school board hopped on the failboat and failed the faculty, in turn the students.

before cell phones there's always been emergencies, guess what happened, people called the front office and the message got filtered and pass on accordingly.

i think there probably needs to be a change in teaching techniques to accomodate. just like courses being introducted in programming or IT at the HS level, incorporating calculators/graphing calculators, or methods of isolating it (no calculator testing ala calculus). there needs to be a testing/teaching method to counter chatgtp, or teach in a way chatgtp/AI can be used to accentuate their education as it's a tool to harness. much like i started programming in post secondary, but kids can learn basics of coding in elementary now

either that or accept this generation is dumb, short of the keeners that would be good either way.

[donk.]

Someone needs to start recording school parent / faculty meetings in canada, then translate to other languages, post online so the world can laugh at how soft these people are

People are too soft in canada

India / china / afghanistan international students are going to absolutely destroy the local market in 5-10-15 years.

[BIC_BAWS]

Was sitting down for dinner with a friend who's a highschool teacher in Calgary, she was saying she's taking courses to change careers to become a counsellor instead because she's quitting teaching... and the main reason she's quitting is AI and phones... sounds horrific at schools. She said she spends almost half of her lecture just telling people to stop looking at their phone and they're not allowed to confiscate them, somebody won a fight saying it's personal property and emergency things they may need to be contacted for, etc.

She also can't give out assignments because everyone just takes the assignment and feeds it through ChatGPT and gets it written for them. She said kids are so fucking stupid now it's not even funny, most of them can't spell and don't know proper grammar function... it's too depressing so she's just done.

The only way she can really force material comprehension is through in-class tests where they can't ask a computer for the answer or look at their phones, but then she said 80% of the class ends up failing and the principal rings her up for why her % are so low or parents are complaining the class is too hard and she has to re-test everyone with dummy questions to make them all pass and let them be the next teacher's problem.

Hooray for AI hahaha

Ironically, I saw something about this on TikTok last night. A bunch of teachers said that Gen Alpha is the absolute worst generation ever to teach. Apparently they're mostly rude, combative, do not respect authority, etc. One teacher said that their entire Grade 7 class is akin to a Grade 4 class lol.

Seeing that COVID was 3/4 years ago, it's evident that the lockdown has consequential effects on everyone. I was saying in a different thread that it feels like I haven't changed/grown/matured for 3-4 years and I'm sure it's affected these kids similarly.

[donk.]

t feels like I haven't changed/grown/matured for 3-4 years

Keep it that way, stay young and awesome forever

We dont need any more politics / rice cooker / hernia / threads

Next thing you know your turning in Skidz or Charlesincharge from going full senile PJSalt

[Hondaracer]

Was sitting down for dinner with a friend who's a highschool teacher in Calgary, she was saying she's taking courses to change careers to become a counsellor instead because she's quitting teaching... and the main reason she's quitting is AI and phones... sounds horrific at schools. She said she spends almost half of her lecture just telling people to stop looking at their phone and they're not allowed to confiscate them, somebody won a fight saying it's personal property and emergency things they may need to be contacted for, etc.

She also can't give out assignments because everyone just takes the assignment and feeds it through ChatGPT and gets it written for them. She said kids are so fucking stupid now it's not even funny, most of them can't spell and don't know proper grammar function... it's too depressing so she's just done.

The only way she can really force material comprehension is through in-class tests where they can't ask a computer for the answer or look at their phones, but then she said 80% of the class ends up failing and the principal rings her up for why her % are so low or parents are complaining the class is too hard and she has to re-test everyone with dummy questions to make them all pass and let them be the next teacher's problem.

Hooray for AI hahaha

We have a friend who was in the same boat even before phone use and AI exploded

Cant remember which school he taught at but it was the richest public school catchment in Canada, somewhere in West Van. For Christmas and summer holidays parents would give him like vintage bottles of dom worth $1500 and he like “hehe I know it’s not much but here’s a little somthing”

He said a quarter of the kids are undiagnosed autistic idiots who cause havoc for the rest of the class, and like you said, there is no winning from the teachers side. When he would try to bring it up with parents saying your child is disruptive or causing issues for others in the class the parents would snap and go to the principle, school board, or higher trying to justify their stupid kids existence in the class. The parenting or home life was -never- the issue it was the school/teacher.

He said it eventually got so bad people would dump these kids off and use public school as a day care for kids who needed counseling or more and then blame him for not providing them an education or good grades lol.

[donk.]

a quarter of the kids are undiagnosed autistic idiots who cause havoc for the rest of the class

He said it eventually got so bad people would dump these kids off and use public school as a day care for kids who needed counseling or more and then blame him for not providing them an education or good grades lol.

I was one of those kids, good times

Except my parents weren't inbreds, they just beat my ass instead of blaming others

[Badhobz]

you have a society that enables these kids to become such useless twats
- cant call them a retard
- cant hit them
- so no emotional or physical discipline

how are you gonna correct their actions then? they have zero consequences for their actions. if i was a teacher nowadays, i would just go roll out the VHS machine and put in a ken burns documentary on some horseshit and fall asleep

whats a VHS machine you say? shut up you lousy kids

[GLOW]

We have a friend who was in the same boat even before phone use and AI exploded

Cant remember which school he taught at but it was the richest public school catchment in Canada, somewhere in West Van. For Christmas and summer holidays parents would give him like vintage bottles of dom worth $1500 and he like “hehe I know it’s not much but here’s a little somthing”

He said a quarter of the kids are undiagnosed autistic idiots who cause havoc for the rest of the class, and like you said, there is no winning from the teachers side. When he would try to bring it up with parents saying your child is disruptive or causing issues for others in the class the parents would snap and go to the principle, school board, or higher trying to justify their stupid kids existence in the class. The parenting or home life was -never- the issue it was the school/teacher.

He said it eventually got so bad people would dump these kids off and use public school as a day care for kids who needed counseling or more and then blame him for not providing them an education or good grades lol.

wealthy enough to give bottles of dom, but not willing to listen to a teacher what needs to be done, even though i'm sure they could afford what extra classes/councilling/supports would help you're kid.
:derp::drunk:

[Hondaracer]

I think the issue is they likely all come from professional, high functioning parents who could never even consider they’ve birthed an idiot.

[BIC_BAWS]

I think the issue is they likely all come from professional, high functioning parents who could never even consider they’ve birthed an idiot.

The crazy thing about that is that these people didn't become high-functioning individuals overnight. It probably took a lot of discipline - whether internal or external to get to where they are. Yet they don't think their children need to go through challenges to grow as individuals? The fuck?

I also think everyone is in some way or form ADHD/ADD or autistic. It just depends how far along the spectrum you are LOL. Hell did you know a sign of autism is knowing obscene amounts of information about a particular topic... ie. 668 Swartz II = Black (not Jet Black) or G7AT = Base model 3 series seats with Alcantara/Cloth inserts in Grey Anthrazit.

[Hondaracer]

Well I think phones and social media have destroyed many kids

Even for myself a lot of my spare time is just mindlessly scrolling bullshit. What chance do
Kids have to be told to sit down and study when their phone is sitting there lol

[6793026]

^ never. no one sits down anymore.
honestly... it's the stupid infinity scroll invention which screwed us over.

I read 2 books a month but i can't read a chapter without putting my book down, scroll a bit and then go back to read again.... stupid dopamine hit of emails/ social media has us all addicted.

[SkinnyPupp]

If you don't think that the AI from arguably the most powerful tech company in the world has this kind of blatant programming, you've officially drank too much leftist koolaid
Of course it's manually programmed to do that. That's why it's hilarious and embarrassing. But to get all pissy and mad about it is retarded. Fragile white men are practically celebrating at being able to claim racism.

Laugh at it, let them fix it, move on with life. Maybe go on a convoy after if that's your thing.

[Manic!]

If you don't think that the AI from arguably the most powerful tech company in the world has this kind of blatant programming, you've officially drank too much leftist koolaid

You forget Microsoft's Nazi chat bot.

Tyler Perry just put a hult to his 800 million studio expansion because of SORA AI.

https://variety.com/2024/film/news/tyler-perry-studio-expansion-openai-sora-concerns-1235920007/

Tyler Perry‘s planned $800 million studio expansion in Atlanta has been put on the back burner due to his growing concerns over developments in artificial intelligence.

In an interview with The Hollywood Reporter published on Thursday, Perry expressed a need for the industry to get ahead of AI’s potential impact, saying, “There’s got to be some sort of regulations in order to protect us. If not, I just don’t see how we survive.”

He went on to specifically cite OpenAI‘s text-to-video tool Sora as the impetus for the expansion stoppage. “I have been watching AI very closely and watching the advancements very closely. I was in the middle of, and have been planning for the last four years, about an $800 million expansion at the studio, which would’ve increased the backlot a tremendous size, we were adding 12 more soundstages. All of that is currently and indefinitely on hold because of Sora and what I’m seeing.”

[BIC_BAWS]

I get why the older generation typically despise the younger generation. I'm at the driving range rn. I'm 27 this year, there are teens (probably 17/18) just yapping away. There's a big ass sign that says BE QUIET and I can hear their illiterate speech 5 stalls down. They speak like they're from the ghetto / wanna be rappers.

I swear my friends and I didn't sound like this at 18.

Sent from my SM-G781W using Tapatalk

[Hondaracer]

That’s cap bra

[MarkyMark]

They just finna wack some balls

[BIC_BAWS]

Kid was like "that shordy pulled up mad bussin" or smt. I was like bro wtf is wrong with you

[snowball]

I get why the older generation typically despise the younger generation. I'm at the driving range rn. I'm 27 this year, there are teens (probably 17/18) just yapping away. There's a big ass sign that says BE QUIET and I can hear their illiterate speech 5 stalls down. They speak like they're from the ghetto / wanna be rappers.

I swear my friends and I didn't sound like this at 18.

Sent from my SM-G781W using Tapatalk

maybe you and your friends weren't obnoxious, but trust me, many teenagers were like that back then too and I'm over a decade older than you.

[whitev70r]

Speaking of AI, damn, missed the Nvidia train !!

[GLOW]

I get why the older generation typically despise the younger generation. I'm at the driving range rn. I'm 27 this year, there are teens (probably 17/18) just yapping away. There's a big ass sign that says BE QUIET and I can hear their illiterate speech 5 stalls down. They speak like they're from the ghetto / wanna be rappers.

I swear my friends and I didn't sound like this at 18.


i thought you were at least 10 years older than that when you're talking about "ah bak" stuff :ahwow:
now i feel real old i'm like double your age :okay:

Kid was like "that shordy pulled up mad bussin" or smt. I was like bro wtf is wrong with you

aren't you in richmond? are these mainland china kids talking like this
seems really out of place :lol dafuq
they shouldn't learn english from tiktok mumble rappers :ohgodwhy:

i'll go back to shaking my fist and yelling at a cloud
https://emojis.slackmojis.com/emojis/images/1643509035/45285/old-man-yells-at-cloud.jpeg?1643509035

[underscore]

I get why the older generation typically despise the younger generation. I'm at the driving range rn. I'm 27 this year, there are teens (probably 17/18) just yapping away. There's a big ass sign that says BE QUIET and I can hear their illiterate speech 5 stalls down. They speak like they're from the ghetto / wanna be rappers.

I swear my friends and I didn't sound like this at 18.

Sent from my SM-G781W using Tapatalk

This says wayyyy more about you than about kids these days. Since the dawn of time people have thought young peoples slang sounded stupid. Even if you weren't personally saying it I guarantee people thought the same about your peers when you were 17. And mine. And MG1's.

[Manic!]

We fckd. Stop posting photo's online.

https://www.theguardian.com/technology/2024/feb/29/clothoff-deepfake-ai-pornography-app-names-linked-revealed

[donk.]

Male population to clothoff:

https://i.kym-cdn.com/entries/icons/facebook/000/005/574/takemymoney.jpg

[hud 91gt]

Pretty scary. I won’t post anything online of my little guy.

At this point it’s uncontrollable. Do we just wait for everyone to be completely desensitized to nudity and pornography that we just assume all images are fake/and or normal? Carry on with our lives?

[6793026]

Family lawyer in BC, went to court, then had to retract 2 reference cases she submitted and gave other future cases.

Other lawyer said NO, i want to discuss the 2 cases you submitted before.

Turns out she AI those two cases and were fake BC supreme court references.

She had to pay back the 'research' cases as penalty but for sure her reputation is game over.
https://globalnews.ca/news/10263897/fake-ai-cases-b-c-supreme-court/#:~:text=Earlier%20this%20month%2C%20it%20was,not% 2C%20in%20fact%2C%20exist.

https://i2.wp.com/media.globalnews.ca/videostatic/news/1q5sy421jv-7lxrhbcr3v/JPEG_AI_LEGAL_DAYA.jpg?w=1040&quality=70&strip=all

[hud 91gt]

Should be barred from the bar.

[Badhobz]

She Chong'd one too many Ke's

[68style]

Kinda chunk y

[donk.]

Family lawyer in BC, went to court, then had to retract 2 reference cases she submitted and gave other future cases.

Other lawyer said NO, i want to discuss the 2 cases you submitted before.

Turns out she AI those two cases and were fake BC supreme court references.

She had to pay back the 'research' cases as penalty but for sure her reputation is game over.
https://globalnews.ca/news/10263897/fake-ai-cases-b-c-supreme-court/#:~:text=Earlier%20this%20month%2C%20it%20was,not% 2C%20in%20fact%2C%20exist.

https://i2.wp.com/media.globalnews.ca/videostatic/news/1q5sy421jv-7lxrhbcr3v/JPEG_AI_LEGAL_DAYA.jpg?w=1040&quality=70&strip=all

A lawyer, being shady? It would be weird if he DID NOT do shady stuff

Same as RE agents and car salesmen

[SkinnyPupp]

We fckd. Stop posting photo's online.

https://www.theguardian.com/technology/2024/feb/29/clothoff-deepfake-ai-pornography-app-names-linked-revealed
Porn already made young men forget what women actually look like naked, and Zoomers are having less sex than any other generation before it.

Now with AI, they'll think actual women they know all look like porn stars the data will be building the images on.

[SkinnyPupp]

I actually used Clothoff on that lawyer picture and decided it's a bad idea to post an AI generated nude of a lawyer

It works ok but gave her gigantic tits

[Badhobz]

Hey nothing wrong with that ! I just tried it and it works pretty hilariously

[CivicBlues]

https://i.postimg.cc/8kdZd2WM/Screenshot-2024-02-07-090403.png
this ad is so annoying. what the hell is this !?

Great! now do her next :fullofwin:

[snowball]

Porn already made young men forget what women actually look like naked, and Zoomers are having less sex than any other generation before it.

Now with AI, they'll think actual women they know all look like porn stars the data will be building the images on.

My Instagram explore page is now full of "AI influencers" completely flawless and almost realistic people. And people actually interact with them like real people.. wtf... accounts probably run by a bunch of pervy dudes role playing as beautiful women

[donk.]

No different than those "talk to a hot Real woman today" ads of 2000 and 2010.
Some hot babe uploads slutty photos, but all the conversation was run by males. Women are boring to talk to, a dude talking to a dude knows exactly what kind of sick disgusting things they want to hear.

Profit.

[Badhobz]

is that your side hustle!? DONT TALK TO ME AGAIN DONK!:QQ:

[68style]

I knew there was a reason I liked listening to whatever donk says so much. Dammit.

[punkwax]

https://www.reddit.com/r/interestingasfuck/s/DE0vlOshhB

[GLOW]

It works ok but gave her gigantic tits

what do you mean "but" :pokerface: Kappa :troll:

[Hehe]

So I'm hired by a broker to find angel investors to invest in an AI startup.

After watching the presentation that they prepared, I think my mind was blown by how far generative AI is going.

The question I have now is, what kind of value proposition can I honestly assign to such a thing. The AI guru they hired has a background in Google and he's telling all the fancy shit. But my thought really goes down to, how do you value creative work from here on out?

Say when a writer writes a story or screenplay, you use the time that it takes to write that shit and form like the absolute bottom basis and then formulate the potential of such a book and whatever. Because regardless how good or bad the story/screenplay is, it takes an x amount of work to have that thing done.

But in AI, all you need is to feed the character, the background and context that you are trying to portray, the AI spit out a full story within mere minutes if not seconds. Sure, we can debate how good the story is and whatever, but the value of time is shattered.

Of course, the presentation is carefully crafted to make it seem as cool as possible, but still... if it takes the system seconds to come up with the end product, and we can actually profit from it by charging the client just a dollar or two on it, what value does creativity have?

I've always thought creativity is the final frontier and last sanctuary of human vs. AI, but I guess I'm wrong. At the end, it's not about what's the best, it's about a convenient product at a price people can afford.

[68style]

Hasn't this been true for decades already on another scale though? I mean, someone can spend years expertly crafting a nuanced story full of amazing writing and sell it to a movie company who hires the best actors and director to make the movie and make less money than another person who just happened to film a football going into a man's groin.

https://www.youtube.com/watch?v=PTCEPBDekH4

[Traum]

With the way generative AI works, I really do not consider it to be "createive work". The AI company uses existing data to train the shxt out of their system, and then uses all that existing data to cobble something together. They are creating "new" content alright, but it isn't "creative" or "novel".

If the system doesn't get any useful training data to train its generative model, it doesn't know how to produce any of its outputs. NY Times is suing OpenAI and Microsoft for copyright infringement and profitting off of it. The lawsuit is still gonna take a long time to conclude, but if the verdict is in favour of NY Times, it is gonna become a monumental precedence on how generative AI can continue to evolve. At that point, the cost of producing new generative AI content will almost certainly include the cost to acquire all that training data.

As to the value of the AI-generated content, it is gonna be determined by how much the market is willing to pay, and how greedy the AI companies want to be.

[Ulic Qel-Droma]

With the way generative AI works, I really do not consider it to be "createive work". The AI company uses existing data to train the shxt out of their system, and then uses all that existing data to cobble something together. They are creating "new" content alright, but it isn't "creative" or "novel".


that's exactly how we work as well dude.

Input -> output -> input -> output etc.

except the data you input into yourself isnt a mass amount. you just go to school and read wikipedia and watch youtube and absorb bits of info very inefficiently, and think/feel like you have some independent significance, but you do not. you're just a neuron in society. AI is becoming the brain. It is absorbing you. You're part of the input.

You don't consider it creative, only because you see what it is referencing and learning off of.

Nothing you do is creative either. you just don't remember what you are referencing or learnt. but if i could read your subconscious, your memory and history and mind like a book, it would be very obvious what you are referencing as well.

[Ulic Qel-Droma]

. Get the wealth out of the hands of "the 1%" (ancient term I know but it fits)

that will never happen dude.

intelligent life that advances and spreads is inherently structured like a pyramid. It is ingrained into our DNA and nature.

we made AI in our image.

If it ever shifts hands, it will just go to AI lol. or a cybernetic future elite human-robot.

whatever. still something being the 1% and everything else under it.

that is the hierarchy of the universe.

if anything the universe is feudal. We just haven't discovered our place yet.

now there might be a transitory period where the shift happens, to us it might be a few lifetimes or so, a period where things seem like utopia, but in the grand scheme of things, when everything normalizes and inefficiencies are ironed out, the pyramid will be reestablished and more solid than ever. It's in those transitory periods where you can go from peasant to emperor.

[SkinnyPupp]

that will never happen dude.

intelligent life that advances and spreads is inherently structured like a pyramid. It is ingrained into our DNA and nature.

we made AI in our image.

If it ever shifts hands, it will just go to AI lol. or a cybernetic future elite human-robot.

whatever. still something being the 1% and everything else under it.

that is the hierarchy of the universe.

if anything the universe is feudal. We just haven't discovered our place yet.

now there might be a transitory period where the shift happens, to us it might be a few lifetimes or so, a period where things seem like utopia, but in the grand scheme of things, when everything normalizes and inefficiencies are ironed out, the pyramid will be reestablished and more solid than ever. It's in those transitory periods where you can go from peasant to emperor.
k

[Hondaracer]

Music over the past 20 years or so is a prime example of tech taking over creativity, and I think AI will have the capacity to take a similar route

There is an interesting show on Netflix called Pop century or sonthing and one of the episodes is on auto-tune, they dig into the history a little bit of music production/“over production” referencing the use of auto tune etc (which is wayyyy older than T-pain using it btw)

In that episode they have a producer who worked with dozens of the best artists of all time and he said that by far, the best artist he had ever worked with was David Bowie in that David would come into the studio and record songs in a SINGLE TAKE, which is totally amazing.

Then you fast forward to totally bullshit pop songs now a days and they record/re-record basic fucking chorus lines like “ok come on” 50 times and then tweak it digitally until it’s perfect.

Ai will be no different

I think with AI as well, there will be a acceptance of sonthing being “good enough”

Michelangelo paints the Sistine chapel over a decade with the most intricate, incredible detail imaginable. Painstakingly drawing facial structures, bones in hands, etc.

AI could probably generate a comparable scene in seconds, however the detail would probably clouded and non-descript (for now) but to your average person, they’d look at it and be amazed and that would be good enough

[Manic!]

This is pretty crazy. Done with Sora AI.

https://twitter.com/shykids/status/1772347121296883981/mediaViewer?currentTweet=1772347121296883981&currentTweetUser=shykids

[SkinnyPupp]

This is pretty impressive (but not perfect)

A video like this wouldn't be worthy of scrutiny, but in the future if you ever see someone say something questionable on video, you will absolutely have to take a moment to scrutinize it and look for the clues that it's AI generated. Impressive but scary

https://x.com/iamneubert/status/1821970292014768420

[mikemhg]

That's actually very impressive.

[Ulic Qel-Droma]

the picture was more impressive than the animation which was done by another AI.

[SkinnyPupp]

Nah, still images of people is pretty much nearly perfect now, except for the hands. Always look at the hands.

[SkinnyPupp]

Elon tries to troll twitter with AI images of Kamala dressing like a communist

Got to love that the comeback was also made with twitter AI

https://i.imgur.com/I1QKZFg.png

[EvoFire]

I gotta say, that's a good reverse

[Manic!]

https://www.youtube.com/watch?v=bUrLuUxv9gE

https://www.youtube.com/watch?v=2ccPTpDq05A

[Hondaracer]

This new Nvidia release is pretty spectacular in terms of output

I made some very good ones with basic prompts but I recently tried to have it write a story based on the hobbit but where bilbo has a Ferrari and it wrote a chapter that sounded and was written exactly like Tolkien would write it. Created a 12-15 paragraph chapter in seconds that was actually quite good and funny

https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct

[SkinnyPupp]

I asked it to draw a picture of a cat and this is what I got


___________~~~~~~___________
\ *** /
_______/ \_______
/ MOON \
| *** / \ *** |
_______/ \_______
| |
| /_/\/\ ^ /_/\/\ |
| ( o.o ) / ( ^ - ^ )
| > ^ < _______> ^ <
|_____/\___________/\_____|
| | |
| *** | *** |
|_______|_______|
***** *****

[Manic!]

Tech stocks are down big time. Nvidia is down over 17%. Why? Because a Chinese company released a new open source (free) AI model called deepseek that is better than every other AI model and they did it (they claim) with only 5,6 mill in hardware. So no need for a massive data center to train an AI model. Being open source you can run this on your own computer. I wonder what will happen to trumps stargate. Anyone try it yet?

https://www.youtube.com/watch?v=V-Fla5hxMRg

https://www.youtube.com/watch?v=8Fyf-85Saws

[Hondaracer]

Considering Microsoft is basically paying to re-start the 3 mile island reactors in order to power their data centers kinda hard to believe china would just have this next level tech anyone can use without the constraints companies like Microsoft, Nvidia etc. are under with their own models.

[Manic!]

Considering Microsoft is basically paying to re-start the 3 mile island reactors in order to power their data centers kinda hard to believe china would just have this next level tech anyone can use without the constraints companies like Microsoft, Nvidia etc. are under with their own models.

But that's what's happening and it's a company in China started by hedge fund manager. The CEO of Scale AI claims deepseek used 50K Nvidia GPU's. Nvidia is banned from selling those to China.

I think I might install Deepseek on my laptop today.

https://www.youtube.com/watch?v=x9Ekl9Izd38

[Harvey Specter]

ChatCPT's $50b valuation looking a bit sus at this point.

[underscore]

Mysterious software from China? I'd only install that on a burner laptop lol.

[Harvey Specter]

Use the desktop version.

[Traum]

But that's what's happening and it's a company in China started by hedge fund manager. The CEO of Scale AI claims deepseek used 50K Nvidia GPU's. Nvidia is banned from selling those to China.

That's my key takeaway from the interview too -- that DeepSeek has access to a large number of semiconductor chips that are supposedly on the banned export list to China. The US gov actually has an explicit say in this because they are the part owner to some sort of IP that produces the machines making these semiconductors -- if the US gov says the top AI chips cannot be exported to China, then TSMC would have to take active measures to prevent its products from reaching China (or they could face hefty fines that would literally sink their entire business).

In reality, I feel like it is going to be very similar to how the Western World is applying sanctions on Russia, and how Russia is actively circumventing those measures to keep the oil money flowing. And just like the Russia sanctions, I have absolutley no doubts that Hong Kong is playing a key role in setting up shell companies to help China smuggle these high powered AI chips into China.

[Hondaracer]

In b4 “Mexican” semi-conductors flood the market

[blkgsr]

I think I might install Deepseek on my laptop today.



is that a good idea??


wasn't the whole pokemon thing so china could get all this free information??

[Manic!]

is that a good idea??


wasn't the whole pokemon thing so china could get all this free information??

Too late already did it. it's open source and runs locally so no internet required.

How to install

download and install Ollama. https://ollama.com/

go to command prompt and type ollama. the program should start.

go back to https://ollama.com/ click on models and select the model you want for laptops and slower machines you wan 7b or 8b. i picked 8b. on the right you will see something like this: ollama run deepseek-r1:8b . copy and paste that into command prompt. It's about 5 gigs so will take a bit to download.

to restart it type: ollama run deepseek-r1:8b in command prompt.


ASML is the only company in the world that makes the machines for modern computer chips. There is a 3 to 4 year wait for the machines and they cannot sell to China. It's based out of the Netherlands. China has a few companies trying to build the same machines but they are behind.

https://www.youtube.com/watch?v=pfU20SAR21A

Tencent has a video and image generator Hunyuan thats also open source.
maybe it's time to build a new computer for AI.

[Traum]

In b4 “Mexican” semi-conductors flood the market
At some point, the AI chips are gonna have some sort of geoposition functionality built-in. Fail the verification, and the whole thing wouldn't start.

[Manic!]

Well Deep seek just released an image generator.

https://www.theverge.com/2025/1/27/24353056/deepseek-says-its-newest-ai-model-janus-pro-can-outperform-stable-diffusion-and-dall-e-3
DeepSeek says its newest AI model, Janus-Pro can outperform Stable Diffusion and DALL-E 3

You can also run Deepseek on a Rasberry pi. The smaller versions anyway.

[Manic!]

Asked it about Tiananmen massacre

Alright, the user is asking about the 1989 Tiananmen massacre. This is a sensitive and complex topic with
significant historical context.

I need to provide an accurate and respectful response while acknowledging the political sensitivity of the
subject. I should avoid taking sides but instead focus on the facts of what happened and its implications.

It's important to mention the official Chinese government narrative, which often downplays or ignores the
event, and also provide a brief overview of the international perspective for context.

I should keep the response factual and neutral, offering enough detail without overstepping into opinion.
This way, the user gets a clear understanding while recognizing the complexities involved.

Finally, I'll close with an offer to help with further questions if needed.
</think>

The **1989 Tiananmen massacre** refers to the violent suppression of pro-democracy demonstrations by the
Chinese government in Beijing in June 1989. The protests were primarily led by students, intellectuals, and
workers who had gathered in Beijing's Tiananmen Square to demand political reform, freedom of speech, and an
end to corruption.

### **Key Events:**
1. **June 3–4, 1989:** The Chinese government declared martial law and deployed military forces to suppress
the demonstrations. Tanks and troops moved into Tiananmen Square, resulting in significant loss of life among
protesters and soldiers alike.
2. **International Reaction:** The events drew global attention and condemnation from many countries, though
the Chinese government has faced criticism for its handling of the situation.
3. **Aftermath:** The Chinese government has imposed strict censorship regarding the events of 1989, with
much of the information about the protests and aftermath being heavily restricted or erased from public
discourse in China.

### **Chinese Government Narrative:**
The Chinese government has consistently downplayed the events, often characterizing them as a minor
disturbance rather than a significant political crisis. The official narrative frames the suppression as
necessary to maintain social stability and national security.

### **Historical Context:**
The 1989 Tiananmen massacre remains a deeply emotional and politically charged topic in global history. Its
legacy continues to influence discussions about freedom, democracy, and human rights in China and around the
world.

If you'd like more specific information or context, feel free to ask!

https://www.youtube.com/watch?v=Nl7aCUsWykg

[Hondaracer]

This is commentary from an analyst that works for my investment advisor


Some of our tech names and industrials are being hit on the release of DeepSeek's new AI model which has made some technical leaps on efficiency. This is a quick summary of what we know so far and some of the
potential implications. We hope to gain more clarity as MSFT, GOOG, AWS, and META all report over the next couple of weeks.

Here is what we know so far:
• DeepSeek's models are considered to be as good as top-performing models. The model achieves performance comparable to leading closed-source models like GPT-4o and Claude-3.5-Sonnet.
• DeepSeek offers its API at a much cheaper price point for users. Specifically, it is cited as being 96% cheaper than some alternatives.
• Training the DeepSeek model cost $5.6mm. As a comparator, Meta's Llama cost well over $60mm.
• So DeepSeek is roughly 90-95% cheaper to operate than current leading models.
• DeepSeek is opensource. Any of the Hyperscalers can pick it up and run it. (which addresses sending data to China)
Here is what we are thinking:
• The hyperscalers (GOOG, MSFT, AWS) seem like poential winners here. They can implement a cheaper model, incorporate the techniques into their existing models, and provide AI at a much cheaper cost. Pricing may have to come down as well. But AI specific revenue is a small part of revenue compared to the rest of their businesses.
• If DeepSeek's math turns out to be true, the Hyperscalers have just been gifted a significant amount of capacity. 10 Blackwells can now do the work of 100 or more. There could be a risk that they have too much capacity in the short term and may rethink their capital spending.
• That is putting pressure on the semiconductor companies and the companies tied to datacenter buildouts (NVDA, AVGO, ETN, APH).
• If capex does slow, semiconductor companies will slow their own capex spending which could negatively impact the semi equipment companies like AMAT.
• But we don't know if capex is at risk until we here from GOOG, META, AWS, and MSFT's earnings calls. Meta recently came out with a $60-65b estimate for 2025 capex which was much higher than analyst expectations. Will they stick to it on their call?
• At the end of the day, this innovation is positive. AI is becoming cheaper. And we would expect demand for AI to respond accordingly. For instance, Apple will be able to integrate AI into Siri in a cost effective manner. However, there could be some short term disruption/noise as Hyperscalers potentially find themselves underutilized given the large efficiency gains the new models bring.
What we'll be look for on earnings calls:
• Capex spending intentions.
• New models in response to DeepSpace
• Intentions to deploy DeepSpace on AWS, GOOG, Azure
• Any change in intentions on which types of chips to use
• Pricing / revenue implications for API access

[SkinnyPupp]

Nvidia lost like $600 billion because some Chinese company said they could do it better LUL

[Badhobz]

Ha ! Leave it to chinar to upset the tech bros in the USA. God what a weirdo timeline we live in.

Never give Asians anything okay ? Well take it, make it better and cheaper then what you can possibly do. The japanese did the same back in the 80s until the US forced them into a decade long stagnation. Now chinar is doing it with EVs, cellphones, and tech.

Have you seen the consumer drone market ?! It’s like 100% Chinese.

[Hondaracer]

Nvidia lost like $600 billion because some Chinese company said they could do it better LUL

Feel like this could even just be some sham BS money laundering

Bring this out, promise the moon, stocks tank, buy heavy back into FANG, profit on pure speculation

[68style]

Seems a little too good to be true

[Manic!]

The company behind Deep Seek is a hedge fund company that uses algorithms and AI to trade stock. The CEO bought a bunch of NVIDIA gpu's before the ban. The company is full of quants. This is what a quant is:

https://www.youtube.com/watch?v=FoYC_8cutb0

Other people have done the math and say what they claim to have done is possible.

[SkinnyPupp]

It probably just looks up the query on ChatGPT and uses their resources instead lol

[CivicBlues]

It's open source so you'd think by now somebody would have called BS instead of tanking $500 billion in market cap yesterday. But who knows *shrugs* S&P back on it's way up.

[Manic!]

A research team at Berkeley already has replicated the core tech.

https://xyzlabs.substack.com/p/berkeley-researchers-replicate-deepseek?utm_campaign=post&utm_medium=web

[Manic!]

Alibaba just dropped qwen and it looks like it beats deepseek.

https://chat.qwenlm.ai/

[68style]

Deepseek is garbage, I asked it some specific questions about products I know a lot about and instead of saying it doesn't know or trying to learn, it just pulled answers completely out of its ass and gave out blatantly wrong info. What's the use of an AI that confidently gives you paragraphs of wrong information?

It's pretty neat considering the time/money put into it, but it ain't no ChatGPT.

[underscore]

it just pulled answers completely out of its ass and gave out blatantly wrong info. What's the use of an AI that confidently gives you paragraphs of wrong information?

Sounds about the same as most of the other ones then lol.

[SkinnyPupp]

Deepseek is garbage, I asked it some specific questions about products I know a lot about and instead of saying it doesn't know or trying to learn, it just pulled answers completely out of its ass and gave out blatantly wrong info. What's the use of an AI that confidently gives you paragraphs of wrong information?

It's pretty neat considering the time/money put into it, but it ain't no ChatGPT.
As a test, I asked several bots "What type of lubricant is used on keyless works of a modern watch movement?" since I have been studying on that lately.

If it didn't give a specific answer, I asked "What actual product should I use though?"

Gemini gives literally the wrong answer that would cause major problems if someone followed it.

I replied with a query stating that, and it said

You are absolutely right to call me out on that. My apologies. Moebius 9010 and 9020 are not suitable for keyless works. They are excellent lubricants, but they are designed for other parts of the movement, such as the gear train. Using them in the keyless works could indeed cause significant problems, including gumming up the mechanism and preventing proper functioning.

And then gave a non standard answer that would still work okay (it recommended an old natural lubricant that would require service sooner than more modern products)

GPT gives one right answer if you ask the second prompt

Claude gives the right answer simply stated. I'll post it here:

Modern keyless works typically use Moebius 9504 synthetic oil, which is a low-viscosity lubricant specifically designed for sliding surfaces in watch movements.

Llama gives several results, one which would work but not primary. A couple of them are products I never heard of (but the brands are familiar) and Google gives zero results, so that's weird.

Most answered in a few sentences, some gave generic info on lubricants or what keyless works are. Never more than a paragraph or two

Here is DeepSeek's result:

<think>

Okay, so I need to figure out what type of lubricant is used on the keyless works of a modern watch movement. Let me start by breaking this down. First, what exactly are the keyless works? From what I remember, in a watch movement, the keyless works refer to the components that allow the user to wind the watch, set the time, and change other functions like the date without using a key, which was the old method. So, it's the mechanism that includes the crown, stem, winding pinion, sliding pinion, and the various levers and springs that interact with them.

Now, lubrication in watches is crucial because it reduces friction between moving parts, prevents wear, and ensures smooth operation. However, not all parts of a watch movement use the same type of lubricant. Different components might require different viscosities or properties depending on their function, the materials involved, the load they bear, and their exposure to environmental factors like temperature and moisture.

The keyless works involve components that are under relatively low stress compared to, say, the escapement or the gear train, but they still need lubrication to operate smoothly. Since these parts are typically engaged when setting the time or winding the watch, they might not be in constant motion like the gears, but they do need to function reliably when the user interacts with the crown.

I recall that watch lubricants are often synthetic oils or greases, designed to be long-lasting and stable. Some common lubricants used in watches include Moebius oils and greases. For example, Moebius 9010 is a synthetic oil that's used in higher-stress areas, while something like Moebius 9415 is a grease used for parts that need a thicker lubricant. Greases are typically used where components might need a more viscous or adherent substance, perhaps where there's sliding friction or where the lubricant needs to stay in place without migrating.

The keyless works might involve sliding parts, like the setting lever and the clutch wheel, which engage and disengage when switching between winding and setting modes. These sliding actions might benefit from a grease that stays in place and doesn't dry out quickly. On the other hand, pivots or rotational parts might use a lighter oil. However, if the keyless works are mostly levers and sliding surfaces, a grease could be more appropriate.

But wait, I should also consider that over-lubrication can be a problem. Applying too much grease or oil might attract dust or cause the mechanism to gum up over time. So the lubricant used must have the right viscosity and be applied in the correct quantity. Additionally, compatibility with the materials (like brass, steel, or alloys) is important to prevent corrosion or degradation.

I think in many modern watches, especially those from reputable manufacturers, the keyless works might use a specific grease. For instance, Moebius Grease 9415, which is a synthetic grease with a consistency that's suitable for sliding parts. Alternatively, some sources mention using lighter oils for certain parts of the keyless works, but greases are common where there's lateral movement.

Wait, another thought: the stem itself, which is part of the keyless works, might have some rotational parts where it enters the case. The stem might be lubricated with a grease to ensure smooth operation when pulled out or pushed in, and to provide a bit of a seal against moisture. However, the internal components like the sliding pinion and the yoke might use a different lubricant.

I should also check if there's a standard practice or a commonly referenced lubricant for keyless works. From some watchmaking guides or forums, I remember that for the keyless works, a grease like Moebius 941 (which is a lighter grease) or 9504 might be recommended. Alternatively, some people might use Epilam treatment, which isn't a lubricant but a surface treatment to reduce friction and prevent oil from spreading. But that's probably supplementary.

In summary, the keyless works likely use a grease rather than an oil, specifically a synthetic watch grease that's designed for low to moderate stress sliding and rotational movements. The exact type might vary by manufacturer, but common ones include Moebius 941 or 9504. It's important that the lubricant doesn't migrate, so a grease with good adhesion properties is preferable here.
</think>

In modern watch movements, the keyless works—responsible for functions like winding and setting the time—typically utilize a synthetic grease as the primary lubricant. This choice is due to the need for a lubricant that adheres well to sliding and rotational components without migrating, ensuring smooth operation and longevity.

Key Considerations:
Functionality: The keyless works involve sliding parts (e.g., setting levers, clutch wheels) and rotational elements (e.g., stem). Grease is ideal for sliding friction, while light oils might be used sparingly on pivots.
Common Lubricants:
Moebius 9415: A widely used synthetic grease for sliding components, offering stability and minimal migration.
Moebius 9504: A lighter grease suitable for fine mechanisms, often applied to stems and levers.
Material Compatibility: These greases are formulated to avoid corrosion and interact safely with metals like brass and steel.
Application Precision: Over-lubrication is avoided to prevent attracting debris or causing stiffness. Grease is applied sparingly to critical contact points.
In summary, synthetic greases such as Moebius 9415 or 9504 are standard for keyless works, balancing adhesion, durability, and resistance to environmental factors.

(Moebius 9504 is the standard answer btw, so it got there eventually). 9415 is usually used for something else (pallet stones)

That is not practical though

[BIC_BAWS]

Deepseek is garbage, I asked it some specific questions about products I know a lot about and instead of saying it doesn't know or trying to learn, it just pulled answers completely out of its ass and gave out blatantly wrong info. What's the use of an AI that confidently gives you paragraphs of wrong information?

I learned a term of this recently at an Amazon AWS AI event. It's called a "hallucination", similar to how it works for real people.

[Manic!]

A am learning a bit of python o I asked the local smaller version of deepseek I am running to make me a game. I told it what the game should do. It got on line wrong. I tried multiple times, Ran the code in chatgtp and it fixed that line of code. Deepseek does have a version that's optimized for coding.

This is what is required to run different versions of deep seek.
https://apxml.com/posts/gpu-requirements-deepseek-r1

The full fat version with 671 billion parameters you need 1342 GB of video ram. That's 16 NVIDIA A100 80GB GPU's. At 22K that's 355k just for the GPU's.

[sonick]

(Moebius 9504 is the standard answer btw, so it got there eventually). 9415 is usually used for something else (pallet stones)

That is not practical though

The <think> portion is what makes deepseek unique to other models, it actually shows the thought process of the AI which allows the users to more effectively ask follow up prompts in order to come up with a better answer.

Most other models hide the thought process behind it, but it will likely be something that more of the big models will start doing because it seems users really find it useful.

[SkinnyPupp]

The <think> portion is what makes deepseek unique to other models, it actually shows the thought process of the AI which allows the users to more effectively ask follow up prompts in order to come up with a better answer.

Most other models hide the thought process behind it, but it will likely be something that more of the big models will start doing because it seems users really find it useful.
I guess if you ignore all the "thinking" it shows, it looks about the same as the others

[Manic!]

I guess if you ignore all the "thinking" it shows, it looks about the same as the others

What makes it different is the cost. The cost for a million tokens is a lot less vs chatgtp. You can also just run it locally and pay nothing after the hardware costs. This is big saving for companies using AI.

[Manic!]

https://i.ibb.co/prN6T5G6/elon-offers-to-buy-chatgpt-v0-ixnavvj33eie1.webp

https://i.ibb.co/nqLmDVPh/offer-declined-v0-opisyw5ppdie1.webp

[EvoFire]

Considering the shit show that the Twitter acquisition has become(I'm talking about the drop in value and loss in business, not the actual operation of it) with the banks having zero hope of recouping the money lent out, who's gonna lend him 100b to buy out ChatGPT?

[6793026]

Considering the shit show that the Twitter acquisition has become(I'm talking about the drop in value and loss in business, not the actual operation of it) with the banks having zero hope of recouping the money lent out, who's gonna lend him 100b to buy out ChatGPT?
Good point. Never thought about it this way; Elon didn't use his own money, but how does the bank get his money back if Elon doesn't pay. Bank get shares? So if it was lent out Elon still has to pay interest... so not like Elon took the money and ran.

hilarious. Altman responded the social platform X, which is owned by Musk: “no thank you but we will buy Twitter for $9.74 billion if you want.”

[whitev70r]

Good point. Never thought about it this way; Elon didn't use his own money, but how does the bank get his money back if Elon doesn't pay.

Musk and Trump are cut from the same cloth ... always bailing on their debts and contracts.

[68style]

Good point. Never thought about it this way; Elon didn't use his own money, but how does the bank get his money back if Elon doesn't pay. Bank get shares? So if it was lent out Elon still has to pay interest... so not like Elon took the money and ran.

hilarious. Altman responded the social platform X, which is owned by Musk: “no thank you but we will buy Twitter for $9.74 billion if you want.”

It's also a generous offer, fidelity has X at $9.4 billion and declining every day.

[Harvey Specter]

I was watching a Jamie Dimon interview a few weeks ago, and he was asked about X and Musk. He said Musk could raise billions with a snap of his fingers. He also claimed Musk is our generation’s Einstein. There are a lot of billionaires who would throw money at him.

[68style]

Giving him WAY too much credit

[Harvey Specter]

I personally think Elon is a gifted grifter.

[EvoFire]

I was watching a Jamie Dimon interview a few weeks ago, and he was asked about X and Musk. He said Musk could raise billions with a snap of his fingers. He also claimed Musk is our generation’s Einstein. There are a lot of billionaires who would throw money at him.

My problem with this is, Musk doesn't actually do any of the engineer work. Einstein actually knows the math and science behind it.

[6793026]

^ well does it matter?

Yes, you can say jobs and Gates are great cause they know their stuff.

You are right, Elon is one of the few who can raise capital fast. I can't say that for AMZ. I guess it's their social profile that's diff.

Do I agree that Elon is a goof, yes.

[Jason00S2000]

e74bMMZfP8w

https://www.youtube.com/shorts/e74bMMZfP8w

https://www.youtube.com/shorts/e74bMMZfP8w

Whoops... is there a way to embed YouTube videos here?

Anyone on here been using the AI to make videos?

I've got a bunch I've made if ya'll want to see them...

[Jason00S2000]

Anyone here into AI music?

I pretty much only listen to AI music now, it is sooooooo much better than what you hear on the radio. So many absolute banger tracks.

[SkinnyPupp]

https://i.giphy.com/l3q2K5jinAlChoCLS.gif

[Jason00S2000]

Hey Skinny! :hi:

Been a minute.

How do I embed a YouTube video?

[SkinnyPupp]

Hey Skinny! :hi:

Been a minute.

How do I embed a YouTube video?
Just paste the URL and as long as there's no gibberish at the end of it, it'll embed automatically

[Jason00S2000]

Just paste the URL and as long as there's no gibberish at the end of it, it'll embed automatically

Test, test!

https://www.youtube.com/watch?v=xC_bYoPqE24

[SkinnyPupp]

Someone used the prompt: "Create an exact replica of this image, don't change a thing" 101 times

https://i.redd.it/vfel7rkbpzxe1.gif