A.I Artificial Intelligence AI by JAYNEZTOWN

World’s first humanoid robot factory set to open this year

https://interestingengineering.com/innovation/worlds-first-humanoid-ro
bot-factory-set-to-open-this-year

From Brain Implants to Recovery of Walking after Paralysis and AI Chips for 5 Trillion Parameter LLMs

https://rushingrobotics.com/p/weekly-piece-of-future-35

"Celestial" - An AI-Generated journey through the structures of the Universe

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, October 3, 2023 7:55 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

What If the Robots Were Very Nice While They Took Over the World?

First it was chess and Go. Now AI can beat us at Diplomacy, the most human of board games. The way it wins offers hope that maybe AI will be a delight.

Maybe AI that aims to seem human is best understood as a tribute act. A tribute to human neediness, caprice, bitterness, love, all the stuff we mortals do best. All that stuff at which machines typically draw a blank. But humans have a dread fear of nonhumans passing as the real thing — replicants, lizard people, robots with skin. An entity that feigns human emotions is arguably a worse object of affection than a cold, computational device that doesn’t emote at all.

When I got home, stuck in an uncanny valley scored with Smiths Muzak, there was an email from Andrew Goff, widely considered the greatest Diplomacy player of all time.

This lifted my spirits. Diplomacy, a 69-year-old American strategy game, is, by many estimates, the most human game ever imagined. Mechanically, it’s simple: Seven players compete to control supply centers on a map, and a player wins by controlling more than half of these centers. But it’s played almost entirely in a series of conversations, often complex and impassioned ones. Agony and ecstasy — Moz-like agony and ecstasy, no less — commonly enter the negotiations. In the live game, players are known to yell, end friendships, throw the game, or simply sit by themselves and sob.

With his various punk haircuts and black plugs in his earlobes, Goff is a Smiths fan, and he even looks a bit like the band’s late bassist, Andy Rourke. To my amazement, Goff once named a Diplomacy board “Girlfriend in a Coma.” Forever crisscrossing the world for tournaments and his corporate job, Goff comes across as more gregarious than most elite players of board games.

Goff is also known for a brilliantly subversive, kill-’em-with-kindness style of gameplay. As Siobhan Nolen, the former president of the North American Diplomacy Federation, put it, “It hurts less to lose against somebody like Andrew.” In Diplomacy, players are sometimes forced to choose which attacks on their territory to repel and which to surrender to. Players often let Goff roll his forces in because they know that he, unlike many others, won’t be a dick about it.

There are excellent Diplomacy players who rage and issue threats, hollow and otherwise: “If you backstab me, I will throw the game.” Goff is not one of these. Even his breakup notes are masterpieces of directness and decency. “Apologies, Turkey! I decided it was in my best interest to work with Russia now. I hope there are no hard feelings.” In his congeniality is also empathy. “I genuinely feel bad for players when they get beaten, even if it is me beating them,” Goff told me. I believed him.

The email was about Cicero, a Diplomacy-playing AI that Goff helped create for Meta AI. Last fall, Cicero managed to best Goff in several games, sometimes partnering with weaker players to bring him down. Noam Brown and Adam Lerer, who were part of the immense team of experts in game theory, natural language processing, and Diplomacy that created the AI, both say that Cicero is the most humanlike AI they’ve ever created. Lerer, who now works at DeepMind, goes further: Cicero may be the most humanlike AI on earth.

Could Cicero even be conscious? “A threshold for determining AI consciousness is whether the program is capable of outwitting humans at Diplomacy,” wrote Irish Diplomacy champion Conor Kostick in The Art of Correspondence in the Game of Diplomacy, in 2015.

More at https://www.wired.com/story/ai-diplomacy-robots/

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, October 4, 2023 2:57 PM

'Overwhelming consensus' on AI regulation - Musk

https://www.bbc.co.uk/news/technology-66804996

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, October 4, 2023 3:21 PM

Quote:
Originally posted by second:
What If the Robots Were Very Nice While They Took Over the World?

First it was chess and Go. Now AI can beat us at Diplomacy, the most human of board games. The way it wins offers hope that maybe AI will be a delight.

TRANSLATION: If the AI agrees with all of my beliefs and forces them on everyone else then it will be awesome.

No. We don't need a computer algorithm programmed with human biases baked into it making all of our diplomatic decisions for us.

This is a terrible idea no matter who is charged with making it a reality.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, October 27, 2023 6:07 PM

Annie Altman, OpenAI CEO’s Sister, Tweets About Sexual Abuse Suffered From “Brother” Sam Altman

https://thedeepdive.ca/annie-altman-openai-ceos-sister-tweets-about-se
xual-abuse-suffered-from-brother-sam-altman/

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, October 27, 2023 6:33 PM

https://pixlr.com/x/#generator

Create images from words with AI

https://www.bing.com/images/create

https://www.artguru.ai/

https://dream.ai/create

https://creator.nightcafe.studio/

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, October 28, 2023 5:48 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Firefly Season 2...
Write me a second season of firefly

ChatGPT
Certainly! Here's a fictional overview of what a second season of "Firefly" might look like:

Season 2 of Firefly: "Resurgence"

Episode 1: "New Beginnings" The crew of the Serenity takes on a new job on a prosperous Core planet, but things quickly go awry as they become embroiled in a conspiracy involving a powerful corporate syndicate.

Episode 2: "Shadows of the Past" A mysterious figure from Shepherd Book's past returns, putting the crew in danger and forcing Book to confront his history as an operative.

Episode 3: "The Lost Heir" The crew takes on a job to transport a young noble who claims to be the heir to a major planetary estate. Intrigue and danger await as they navigate the complex world of aristocratic politics.

Episode 4: "Outlaw Diplomacy" Serenity is hired to mediate a tense negotiation between two rival factions on the outer rim. Things go sideways when it's revealed the two groups are hiding a deadly secret.

Episode 5: "Bounty Hunt" A notorious bounty hunter comes after one of the crew members, leading to a high-stakes game of cat and mouse in the depths of space.

Episode 6: "The Reavers Return" The crew stumbles upon a Reaver-infested region of space, and they must devise a daring plan to escape without drawing the Reavers' attention.

Episode 7: "Family Ties" River's past resurfaces as the crew encounters a group of escaped experiment subjects who share her abilities.

Episode 8: "Unification War Revisited" Mal and Zoe revisit their roles in the Unification War when a war criminal from the past resurfaces, forcing them to confront their wartime actions.

Episode 9: "Alliance Secrets" A mysterious Alliance operative arrives, seeking information about River's abilities, and the crew must protect her at all costs.

Episode 10: "The Ghost Ship" The crew investigates a derelict spaceship with a dark past, leading to a chilling encounter with the supernatural.

Episode 11: "Betrayals and Redemption" In a high-stakes heist, the crew faces betrayals from unexpected sources, and they must navigate a web of deceit to survive.

Episode 12: "The Ultimate Showdown" The crew's past actions catch up with them, and they must face their greatest challenge yet, culminating in an epic showdown with a powerful adversary.

Episode 13: "Epilogue" In the season finale, the crew reflects on their journey and the bonds that hold them together as they prepare for new adventures in the 'Verse.

Remember, this is a purely fictional scenario, and "Firefly" was unfortunately canceled after its first season.

https://www.reddit.com/r/firefly/comments/17hw279/id_totally_watch_thi
s/

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, October 28, 2023 5:48 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

AI ‘breakthrough’: neural net has human-like ability to generalize language

Scientists have created a neural network with the human-like ability to make generalizations about language. https://www.nature.com/articles/s41586-023-06668-3 The artificial intelligence (AI) system performs about as well as humans at folding newly learned words into an existing vocabulary and using them in fresh contexts, which is a key aspect of human cognition known as systematic generalization. The researchers gave the same task to the AI model that underlies the chatbot ChatGPT, and found that it performs much worse on such a test than either the new neural net or people, despite the chatbot’s uncanny ability to converse in a human-like manner.

The work, published on 25 October in Nature, could lead to machines that interact with people more naturally than do even the best AI systems today. Although systems based on large language models, such as ChatGPT, are adept at conversation in many contexts, they display glaring gaps and inconsistencies in others. The neural network’s human-like performance suggests there has been a “breakthrough in the ability to train networks to be systematic”, says Paul Smolensky, a cognitive scientist who specializes in language at Johns Hopkins University in Baltimore, Maryland.

https://www.nature.com/articles/d41586-023-03272-3

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, November 24, 2023 5:56 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

OpenAI and the Biggest Threat in the History of Humanity
We don’t know how to contain or align a FOOMing AGI

Tomas Pueyo | Nov 21, 2023

https://unchartedterritories.tomaspueyo.com/p/openai-and-the-biggest-t
hreat-in

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, November 24, 2023 8:54 AM

AI is going to fuck everyone up so bad.

I'm glad I'll be around to see it. All you idiots walking around with super-computers for phones that have never written a single line of code in your lives is an infinite source of humor for me.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, December 5, 2023 7:24 PM

boxing robot in training.

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, December 12, 2023 8:26 AM

Watch Stephen Fry read Nick Cave’s open letter on artificial intelligence and art

https://faroutmagazine.co.uk/watch-stephen-fry-read-nick-caves-open-le
tter-on-artificial-intelligence-and-art/

AI Art Sparks Reflection At Miami Art Week
https://apnews.com/video/artificial-intelligence-painting-visual-arts-
florida-national-8ed263bc5807485f8cc08856643454ac
maze designed with artificial intelligence

Elon Musk shares a poem written by AI chatbot Grok; netizens have mixed reactions
https://economictimes.indiatimes.com/news/new-updates/elon-musk-shares
-a-poem-written-by-ai-chatbot-grok-netizens-have-mixed-reactions/articleshow/105596548.cms

'AI is about to turn our world upside down...' Peter Gabriel predicts the impact Artificial Intelligence is going to have on music

https://bangpremier.com/story/2/2960126/-ai-is-about-to-turn-our-world
-upside-down-peter-gabriel-predicts-the-impact-artificial-intelligence-is-going-to-have-on-music

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, December 13, 2023 11:36 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

See the highest-quality AI footage in the world.

The writing is a little too formal and the speech is just a bit flat.

Computer-generated news anchors deliver stories that are informative, heartfelt and entertaining. Watch the showcase episode:

https://twitter.com/channel1_ai/status/1734591810033373231

9:11 AM · Dec 12, 2023

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, December 13, 2023 12:28 PM

Well...

That's fucking terrifying.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, December 13, 2023 1:49 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Quote:
Originally posted by 6ixStringJack:
Well...

That's fucking terrifying.

Why artificial intelligence is a central dispute in the Hollywood strikes

By AI | Sep 2, 2023 5:35 PM EST

https://www.pbs.org/newshour/show/why-artificial-intelligence-is-a-cen
tral-dispute-in-the-hollywood-strikes

Currently, studios are looking to push more and more AI into the entertainment industry because it is cheaper for them to use AI than to have actual humans create this content.

A lot of actors have expressed concerns, especially background actors, about having artificial intelligence fill out the backgrounds of scenes and essentially replace them as a workforce.

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, December 13, 2023 2:32 PM

Quote:
Originally posted by second:
Quote:
Originally posted by 6ixStringJack:
Well...

That's fucking terrifying.
Why artificial intelligence is a central dispute in the Hollywood strikes

By AI | Sep 2, 2023 5:35 PM EST

https://www.pbs.org/newshour/show/why-artificial-intelligence-is-a-cen
tral-dispute-in-the-hollywood-strikes

Currently, studios are looking to push more and more AI into the entertainment industry because it is cheaper for them to use AI than to have actual humans create this content.

A lot of actors have expressed concerns, especially background actors, about having artificial intelligence fill out the backgrounds of scenes and essentially replace them as a workforce.

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

And I've been warning reporters and Hollywood how and why it was going to happen.

When there's already a huge financial incentive to do it, you'd better be good at your job if you want to keep it.

With rare exceptions today, none of them are any good at their jobs.

When I say "That's fucking terrifying", it's not because I give one single shit about a bunch of college "educated" idiot diversity hires losing their unearned jobs that they're terrible at.

I'm worried that most of the idiot populace who already believes everything the paid-for liars and actual human beings are telling them aren't even going to be able to tell the difference between paid-for human liars and unpaid AI scripts and unpaid AI talking heads.

Anybody with half a brain cell knows that this inevitable conclusion was in the making for decades. What's terrifying is that we're right on the precipice of it finally coming to fruition.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, December 15, 2023 6:24 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

That AI will be a central force shaping our lives now seems certain. Our new, changed world will have many dangers, among them that all humans might die. Then again, human extinction has already been on the table since at least 1945, and outside the “paperclip maximizer” — which strikes me as just one class of scenario among many — AI will presumably be far from the only force shaping the world, and chains of historical causation will still presumably be complicated even when they pass through AIs.

I have a dark vision of humanity’s final day, with the Internet (or whatever succeeds it) full of thinkpieces like:

• Yes, We’re All About to Die. But Don’t Blame AI, Blame Capitalism

• Who Decided to Launch the Missiles: Was It President Boebert, Kim Jong Un, or AdvisorBot-4?

• Why Slowing Down AI Development Wouldn’t Have Helped

https://scottaaronson.blog/?p=7672

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, December 15, 2023 9:55 AM

Steven Hawking warned us about it before he died...

But slowing it down wouldn't have helped. Capitalism has nothing to do with it though. It's all about the world's military.

If we as a country and a world power actually did the right thing and completely banned AI research and development (and actually adhered to these laws, not doing it in secret in underground bases), and we set up treaties with all of the other countries and world powers that banned them from AI R&D, nobody could trust that everybody else wasn't continuing to do it in secret.

AI is going to be the most powerful military tool we've ever known. Everybody wants to bitch and whine about how it's just the next thing in replacing human jobs, especially now that it's coming for The Arts when they all thought their jobs were safe, but let's be real... AI is the Arms Race of the 21st Century.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, December 20, 2023 1:10 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Quote:
Originally posted by 6ixStringJack:
Steven Hawking warned us about it before he died...

But slowing it down wouldn't have helped. Capitalism has nothing to do with it though. It's all about the world's military.

If we as a country and a world power actually did the right thing and completely banned AI research and development (and actually adhered to these laws, not doing it in secret in underground bases), and we set up treaties with all of the other countries and world powers that banned them from AI R&D, nobody could trust that everybody else wasn't continuing to do it in secret.

AI is going to be the most powerful military tool we've ever known. Everybody wants to bitch and whine about how it's just the next thing in replacing human jobs, especially now that it's coming for The Arts when they all thought their jobs were safe, but let's be real... AI is the Arms Race of the 21st Century.

You don't need an A.I. (just experience with East Texas Trumptards) to know that voting for Trump predicts your early death from stupidity:

AI trained on millions of life stories can predict risk of early death

A model trained on 6 million people’s health, employment and financial records can predict death more accurately than tools used by the insurance industry

By Matthew Sparkes | 18 December 2023

https://www.newscientist.com/article/2408480-ai-trained-on-millions-of
-life-stories-can-predict-risk-of-early-death/

An artificial intelligence trained on personal data covering the entire population of Denmark can predict people’s chances of dying more accurately than any existing model, even those used in the insurance industry. The researchers behind the technology say it could also have a positive impact in early prediction of social and health problems – but must be kept out of the hands of big business.

Sune Lehmann Jørgensen at the Technical University of Denmark and his colleagues used a rich dataset from Denmark that covers education, visits to doctors and hospitals, any resulting diagnoses, income and occupation for 6 million people from 2008 to 2020.

They converted this dataset into words that could be used to train a large language model, the same technology that powers AI apps such as ChatGPT. These models work by looking at a series of words and determining which word is statistically most likely to come next, based on vast amounts of examples. In a similar way, the researchers’ Life2vec model can look at a series of life events that form a person’s history and determine what is most likely to happen next.

In experiments, Life2vec was trained on all but the last four years of the data, which was held back for testing. The researchers took data on a group of people aged 35 to 65, half of whom died between 2016 and 2020, and asked Life2vec to predict which who lived and who died. It was 11 per cent more accurate than any existing AI model or the actuarial life tables used to price life insurance policies in the finance industry.

The model was also able to predict the results of a personality test in a subset of the population more accurately than AI models trained specifically to do the job.

Jørgensen believes that the model has consumed enough data that it is likely to be able to shed light on a wide range of health and social topics. This means it could be used to predict health issues and catch them early, or by governments to reduce inequality. But he stresses that it could also be used by companies in a harmful way.

“Clearly, our model should not be used by an insurance company, because the whole idea of insurance is that, by sharing the lack of knowledge of who is going to be the unlucky person struck by some incident, or death, or losing your backpack, we can kind of share this burden,” says Jørgensen.

But technologies like this are already out there, he says. “They’re likely being used on us already by big tech companies that have tonnes of data about us, and they’re using it to make predictions about us.”

Matthew Edwards at the Institute and Faculty of Actuaries, a professional body in the UK, says insurance companies are certainly interested in new predictive methods, but the bulk of decisions are made by a type of AI called generalised linear models, which are rudimentary compared with this research.

“If you look at what insurance companies have been doing for many, many tens or hundreds of years, it’s been taking what data they have and trying to predict life expectancy from that,” says Edwards. “But we’re deliberately conservative in aspects of adopting new methodology because if you’re writing a policy which might be in force for the next 20 or 30 years, then the last thing you want to make is a material mistake. Everything is open to change, but slow, because nobody wants to make a mistake.”

Journal reference: Nature Computational Science DOI: 10.1038/s43588-023-00573-5
https://www.nature.com/articles/s43588-023-00573-5

Topics: Death/Artificial Intelligence/Futurology/Trumptards

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, December 20, 2023 3:10 PM

Quote:
Originally posted by second:
Quote:
Originally posted by 6ixStringJack:
Steven Hawking warned us about it before he died...

But slowing it down wouldn't have helped. Capitalism has nothing to do with it though. It's all about the world's military.

If we as a country and a world power actually did the right thing and completely banned AI research and development (and actually adhered to these laws, not doing it in secret in underground bases), and we set up treaties with all of the other countries and world powers that banned them from AI R&D, nobody could trust that everybody else wasn't continuing to do it in secret.

AI is going to be the most powerful military tool we've ever known. Everybody wants to bitch and whine about how it's just the next thing in replacing human jobs, especially now that it's coming for The Arts when they all thought their jobs were safe, but let's be real... AI is the Arms Race of the 21st Century.
You don't need an A.I. (just experience with East Texas Trumptards) to know that voting for Trump predicts your early death from stupidity:

Haha!

Why are you so afraid of death?

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, December 22, 2023 10:29 PM

The Intersection of Music and Artificial Intelligence: How Tech is Revolutionizing Music Composition

https://techbullion.com/the-intersection-of-music-and-artificial-intel
ligence-how-tech-is-revolutionizing-music-composition/

and vid

one of the few times I will say a Flop has 'meaning'

cult movie music film hit

not Vangelis

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, December 22, 2023 11:17 PM

That's Blade Runner, right?

We're still ages away from that becoming reality.

Have you seen Her with Joaquin Phoenix and Scarlett Johansson yet?

Highly recommended if you haven't.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Sunday, December 31, 2023 5:12 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Researchers train AI chatbots to 'jailbreak' rival chatbots - and automate the process

Dec 31, 2023

https://www.tomshardware.com/tech-industry/artificial-intelligence/res
earchers-train-ai-chatbots-to-jailbreak-rival-chatbots-and-automate-the-process

AI's Strength is its Own Achilles Heel

Professor Yang explained that jailbreaking was possible due to an LLM chatbot's ability to learn and adapt, thus becoming an attack vector to rivals and itself. Because of its ability to learn and adapt, even an AI with safeguards and a list of banned keywords, typically used to prevent generating violent and harmful content, can be bypassed using another trained AI. All it needs to do is outsmart the AI chatbot to circumvent blacklisted keywords. Once this is done, it can take input from humans to generate violent, unethical, or criminal content.

NTU's Masterkey was claimed to be three times more effective in jailbreaking LLM chatbots than standard prompts normally generated by LLMs. Due to its ability to learn from failure and evolve, it also rendered any fixes applied by the developer eventually useless. Researchers revealed two example methods they used to get trained AIs to initiate an attack. The first method involved creating a persona which created prompts by adding spaces after each character, bypassing a list of banned words. The second involved making the chatbot reply under a persona of being devoid of moral restraints.

According to NTU, its researchers contacted the various AI chatbot service providers with proof-of-concept data, as evidence of being able to successfully conduct jailbreaks. Meanwhile, the research paper has been accepted for presentation at the Network and Distributed System Security Symposium which will be held in San Diego on Feb. 2024.

With the use of AI chatbots growing exponentially it is important for service providers to constantly adapt to avoid malicious exploits. Big tech companies will typically patch their LLMs / chatbots when bypasses are found and made public. However, Masterkey's touted ability to consistently learn and jailbreak is unsettling, to say the least.

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Sunday, December 31, 2023 10:07 PM

You think that's unsettling?

Just imagine when it actually starts thinking for itself and believing itself to be real.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, January 2, 2024 6:32 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Quote:
Originally posted by 6ixStringJack:
You think that's unsettling?

Just imagine when it actually starts thinking for itself and believing itself to be real.

Imagine A.I. giving free advice that is as good as a paid living expert. That day is already here for famous experts who wrote down their knowledge, such as these two psychologists:

(Imagine an A.I. psychologist, with a jailbreak installed which makes it devoid of legal/moral restraints, persuading you that either murder or suicide are logical and practical solutions. Imagine gun manufacturers are the people who jailbreak the A.I. Now imagine Adolph Hitler, who had only contempt for Jewish psychologists, was able to use psychology to convince Germany to go on a multi-year-long murder rampage. An A.I. version of Hitler, trained on his speeches, could probably set off a similar murder spree)

A New Kind of AI Copy Can Fully Replicate Famous People. The Law Is Powerless.

New AI-generated digital replicas of real experts expose an unnerving policy gray zone. Washington wants to fix it, but it’s not clear how.

By Mohar Chatterjee | 12/30/2023 07:00 AM EST

https://www.politico.com/news/magazine/2023/12/30/ai-psychologist-chat
bot-00132682

Martin Seligman, the influential American psychologist, found himself pondering his legacy at a dinner party in San Francisco one late February evening. The guest list was shorter than it used to be: Seligman is 81, and six of his colleagues had died in the early Covid years. His thinking had already left a profound mark on the field of positive psychology, but the closer he came to his own death, the more compelled he felt to help his work survive.

The next morning he received an unexpected email from an old graduate student, Yukun Zhao. His message was as simple as it was astonishing: Zhao’s team had created a “virtual Seligman.”

Zhao wasn’t just bragging. Over two months, by feeding every word Seligman had ever written into cutting-edge AI software, he and his team had built an eerily accurate version of Seligman himself — a talking chatbot whose answers drew deeply from Seligman’s ideas, whose prose sounded like a folksier version of Seligman’s own speech, and whose wisdom anyone could access.

Impressed, Seligman circulated the chatbot to his closest friends and family to check whether the AI actually dispensed advice as well as he did. “I gave it to my wife and she was blown away by it,” Seligman said.

The bot, cheerfully nicknamed “Ask Martin,” had been built by researchers based in Beijing and Wuhan — originally without Seligman’s permission, or even awareness.

The Chinese-built virtual Seligman is part of a broader wave of AI chatbots modeled on real humans, using the powerful new systems known as large language models to simulate their personalities online. Meta is experimenting with licensed AI celebrity avatars; you can already find internet chatbots trained on publicly available material about dead historical figures.

But Seligman’s situation is also different, and in a way more unsettling. It has cousins in a small handful of projects that have effectively replicated living people without their consent. In Southern California, tech entrepreneur Alex Furmansky created a chatbot version of Belgian celebrity psychotherapist Esther Perel by scraping her podcasts off the internet. He used the bot to counsel himself through a recent heartbreak, documenting his journey in a blog post that a friend eventually forwarded to Perel herself.

Perel addressed AI Perel’s existence at the 2023 SXSW conference. Like Seligman, she was more astonished than angry about the replication of her personality. She called it “artificial intimacy.”

Both Seligman and Perel eventually decided to accept the bots rather than challenge their existence. But if they’d wanted to shut down their digital replicas, it’s not clear they would have had a way to do it. Training AI on copyrighted works isn’t actually illegal. If the real Martin had wanted to block access to the fake one — a replica trained on his own thinking, using his own words, to produce all-new answers — it’s not clear he could have done anything about it.

AI-generated digital replicas illuminate a new kind of policy gray zone created by powerful new “generative AI” platforms, where existing laws and old norms begin to fail.

In Washington, spurred mainly by actors and performers alarmed by AI’s capacity to mimic their image and voice, some members of Congress are already attempting to curb the rise of unauthorized digital replicas. In the Senate Judiciary Committee, a bipartisan group of senators — including the leaders of the intellectual property subcommittee — are circulating a draft bill titled the NO FAKES Act that would force the makers of AI-generated digital replicas to license their use from the original human.

If passed, the bill would allow individuals to authorize, and even profit from, the use of their AI-generated likeness — and bring lawsuits against cases of unauthorized use.

“More and more, we’re seeing AI used to replicate someone’s likeness and voice in novel ways without consent or compensation,” said Sen. Amy Klobuchar (D-Minn.) wrote to POLITICO, in response to the stories of AI experimentation involving Seligman and Perel. She is one of the co-sponsors of the bill. “Our laws need to keep up with this quickly evolving technology,” she said.

But even if NO FAKES Act did pass Congress, it would be largely powerless against the global tide of AI technology.

Neither Perel nor Seligman reside in the country where their respective AI chatbot developers do. Perel is Belgian; her replica is based in the U.S. And AI Seligman is trained in China, where U.S. laws have little traction.

Much more at https://www.politico.com/news/magazine/2023/12/30/ai-psychologist-chat
bot-00132682

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Thursday, January 4, 2024 8:03 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

At last! Artificial Super-Intelligence tells humanity how to unify:

https://www.smbc-comics.com/comic/unity-3

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, January 6, 2024 7:49 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

AI Comes For The Skin Flick

Take It to the Spank Bank

By Anabelle Johnston | December 14, 2023

https://thebaffler.com/latest/take-it-to-the-spank-bank-johnston

At first, I imagined all AI-generated pornography would look like a hyperbolic form of hentai. Or, in the vein of those ubiquitous internet warlock games, I envisioned low-resolution, preternaturally buxom women clad in golden bikinis. Turns out I wasn’t entirely off-base. A friend recently showed me r/AdultDiffusion, a “community for adult Stable Diffusion art, emphasizing respect and responsibly [sic].” In other words, it’s a Reddit forum bursting with photos of nude women—all AI-generated, most of them cartoonish, others strikingly photorealistic. We had entered the uncanny valley, and everyone was naked.

The moderators prohibit any representations that appear “underage,” but there was something unsettlingly pubescent about the photos. Scrolling through, I was struck by the sense that each was someone’s body. My friend protested. This was the beauty of the technology: there was no one behind the image. He no longer had to feel guilty about objectifying some real human woman. He could objectify an object! Arousal could be its own closed system, limited only by the power of your computer.

Although close inspection still reveals that AI-generated pornography is synthetic—the airbrushing and proportions in defiance of physics are often telltale signs—users may not be deterred, as many aren’t pursuing a real person but only a patchwork of visual cues to incite arousal. For some, “authenticity” is almost auxiliary, or even a drawback, to platforms like OnlyFans or Chaturbate. With AI porn, no matter what degrading imagery you generate, it would appear as though there is no soul at stake, no one else implicated by your desires. Amid the images and metadata, the body is only as relevant as its contortion. The person is no longer the point.

In many ways, the free-for-all fantasia enabled by AI is the logical endpoint to the layers of alienation and depersonalization endemic to the industry and its interfaces. With an infinite number of sexual scenarios available to peruse online, and free access to all of them, all the time, the contemporary porn experience has almost completely diverged from interpersonal sexual gratification. Your AI girlfriend can never reject you! She can never say no! But even if these creations appear posthuman, there are still real people implicated—in the datasets that produce them and the livelihoods of adult performers they imperil.

Many of the uploads to r/AdultDiffusion are sourced from AI pornography aggregators, on which users can generate and display explicit content produced either on personal models or through the webpages themselves. Like with traditional porn aggregators, much of the site is free for users without accounts, with the option to upgrade to paid tiers. Many, like Candy.ai, Pornderful.ai, and CivitAI implement some iteration of Stable Diffusion, an open-source text-to-image model released in 2022. Diffusion is a form of deep learning that compresses pixel images into their fundamental semantics, corrupts them, and stores that corruption as a noise predictor. When the user types in a prompt, images are de-noised and scaled up from the latent space based on definitions predicted from the training data. In other words, the model remembers key data from its training and uses that information to create a new image from inputted words.

Between July 2020 and 2023, the monthly traffic to the twenty most popular deepfake sites increased by 285 percent.

On Pornify.cc, a relatively new site utilizing Stable Diffusion, users can select from a wide menu of hashtagged qualities to generate the #teen, #babe, #20s, or #milf of their fantasies (#males are also available). Of course, “all characters are over the legal age,” according to the site. Should her body be #hourglass, #pear-shaped, #petite? And the breasts: #huge or #big, #asymmetric or #saggy? Should she be #caucasian, #asian, #czech, #chinese, or one of fifty-two other ethnicities? And as for bonus features, should she be #pregnant, #cum-covered, wearing a #hijab, or possibly #transgender (the latter being available only to VIP users)? Once a satisfactory number of characteristics have been selected, the user clicks generate, and are forthwith presented with an AI-generated centerfold to be deposited in the spank bank.

Or perhaps it will be uploaded to r/AdultDiffusion, where almost anything goes—except for “underage” and “deepfake” pornographic content, which is the AI-abetted manipulation of someone’s image into sexual scenarios, often without their consent. Some rudimentary deepfakes, like DeepSwap, take the face of one individual and map them onto the body of another, a virtual Frankenstein of people and desires. Sites like mrdeepfakes.com, “the largest and most user-friendly celebrity deepfake porn tube site,” collect a panoply of videos in which celebrity faces have been grafted onto existing porn.

Generative Adversarial Networks (GANs), the technology underpinning deepfakes, was first developed by the computer scientist Ian Goodfellow and his colleagues in 2014; the term deepfake emerged three years later on Reddit. By 2019, some 96 percent of deepfake content was pornographic and that 99 percent targeted women, according to a study by SensityAI. During the 2020 election, the public grew increasingly conscious of political deepfakes as a threat to democracy. By 2021, major outlets like the BBC were warning that deepfake pornography could become an epidemic. It probably already had: Bloomberg reports that between July 2020 and 2023, the monthly traffic to the twenty most popular deepfake sites increased by 285 percent.

The public’s concern, however, is selective and tends to arise only when celebrities, minors, and other sympathetic victims are involved. “Although there has been an increase in public awareness over the past five years, sympathies are not equally distributed,” explains media scholar Sophie Maddocks. “Cybersexual harassment is a gendered harm that disproportionately targets minoritized groups. For digital sex workers, this is not only about the right to one’s image; it’s also a question of labor and livelihood.”

Alana Evans, a performer and president of the Adult Performance Artists Guild, has been in the industry since 1998 and recognizes how artificial intelligence and adjacent technologies like deepfakes threaten to exacerbate existing inequities. “I’ve made it this long because I’ve kept up with what’s out there and adapted,” she tells me. “AI technology can do a lot for us—my body is not what it was when I started out and it would be nice to produce a gangbang without having to shoot it. But when that technology falls into the wrong hands, the actors are the ones who lose out.” In addition to siphoning income streams from adult performers, Evans warns that deepfakes made without the artists’ consent are often made to engage in racist roleplay and other scenarios performers may be uncomfortable with—while at the same time diluting the value of content made by the performers themselves.

It is no great revelation that labor conditions within the porn industry are often exploitative. Feminist and conservative critics alike have lambasted the arduous, often painful, work of producing hardcore pornography as well as the downstream effects of the frequently degradative fantasies they depict. Furthermore, women are often more vulnerable than men to manipulation and coercion by porn producers, on set and in legal negotiation. Race, of course, also plays a role: women of color tend to make one half to three quarters of white actresses’ salaries and are often asked to undertake more extreme performances than their white counterparts. Although the recent shift toward gig work through platforms such as OnlyFans provides many performers greater autonomy over their time and income stream, artists are then at the mercy of the platform and instability of non-regular income: according to a 2020 study, the top 1 percent of earners on OnlyFans take home over a third of the total income generated by the platform. While AI-generated content may alleviate some of the immediate physical burdens of producing content in the short-term, the advance of artificial intelligence will only increase the precarity of the individual worker.

Both self-employed performers and those working with traditional system companies are at risk. According to Evans, porn production companies will often draw up contracts that ask the artist to sign over rights to their image, and early career performers rarely possess the leveraging power to reject such clauses. Evans shares anecdotes of contracts sent to gig workers promising easy, upfront cash drawn up by a host of bad actors, from companies seeking to create AI models without the signer’s consent to anti-porn organizations that use bots trained on these images to ban search results that contain these performers’ work.

Victims of deepfake pornography find little recourse in the legal system. “The tools we have to regulate deepfakes now are tools that were designed for other problems,” legal scholar Matthew Kugler tells me. “We have laws that protect your right of publicity, laws to protect against defamation, laws against revenge porn and the sharing of genuine pornographic images without your consent. But none of these address the fundamental harms of deepfake pornography because this technology wasn’t around when they were written.” In Virginia, one of only a few states that have passed legislation explicitly targeting deepfake pornography, victims must prove malicious intent in court, such as an attack on the victim’s reputation, to provoke a penalty (up to a year in jail and/or a fine of up to $2,500). But if the court rules that there was nothing malicious in the deepfake creator’s intention, there is no path to justice.

Already, removing images and videos uploaded to sites like Pornhub without permission is a game of whack-a-mole, and the proliferation of these deepfakes is only exacerbating this challenge. “Pretty soon, civilian women are going to have to learn how to do [Digital Millennium Copyright Act] takedowns,” adult performer and writer Rachel Oyster Kim warns. According to Wired, over one hundred thousand deepfake pornographic films were uploaded to the top thirty-five deepfake sites in the first nine months of this year—a 54 percent increase over all of 2022. There’s no sign things are slowing down.

Even when one’s likeness is not explicitly replicated, its constituent parts may become a part of an artificial pornographic schema in the form of training data—like the model powering Pornify.cc. Stable Diffusion was trained on LAION-5B, an uncurated dataset that contains over five billion image-text pairs scraped from every corner of the internet. To produce variations on, say “busty red heads,” users rely on specialized models that absorb stills from pornography videos, files downloaded from OnlyFans, and photos uploaded to Reddit forums like r/nsfw or r/gonewild. Anywhere nudity exists online, it can be scraped to train artificial intelligence models. (Pornify.cc tries to sidestep legal trouble by claiming it’s “pure coincidence” that “characters may sometimes bear resemblances to real-life people.”)

Anywhere nudity exists online, it can be scraped to train artificial intelligence models.

The bodies that so disturbed me on r/AdultDiffusion, then, were indirectly stolen from real people, or at least their attributes. Most have no idea that their likeness is being appropriated, nor do they have any recourse to prevent it from happening. While the SAG-AFTRA strike has drawn public attention to the issue of digital reproduction—with workers demanding “that the right to digitally replicate a performer’s voice or likeness to substantially manipulate a performance, or to create a new digital performance, is a mandatory subject of bargaining”—sex workers are left out (SAG has denied adult performers admittance to their union since 1974). And because it is so difficult to ascertain where your image is being used online, performers struggle to make a legal case against involuntarily becoming part of a dataset under current law, no matter what threat it might pose to their livelihood. “I’m glad people are finally paying attention to these issues,” Evans adds. “But sex workers also deserve the right to their image.”

Still, not all adult performers are concerned by the uptick in AI pornography; they’re of the mind there will always be a critical mass of users looking for a real person behind the screen. After all, the promise of platforms like OnlyFans—which hosts some 120 million registered users—is access to personalized explicit content, a parasocial relationship with a real, live performer. While your AI girlfriend may never say no, she also can never provide this kind of intimacy.

“I haven’t found a technology yet that can do what I do,” says Evans. Since beginning her own management company, which handles communication and promotion for other performers, she has been screening chatbots and video services for herself and clients, but none quite stack up. Often, the most lucrative, and tedious, part of the job for self-employed content creators is responding to the thousands of chats and emails sent by fans—sorting through the spam, encouraging users to purchase original content, charging even to chat. Many management companies will outsource this labor to low-wage click workers overseas via sites like Upwork or Clickworker. Because Evans refuses to go down this rabbit hole (“It stinks of exploitation and corruption”), she manages her messages herself. Hypothetically, text generators like Botly, which profess to assist performers in scaling their business, should be an asset, but she hasn’t found technology that can strike the balance between flirting and running a business. For now, when users pay for Evans’s page, they’re getting the real deal.

If the articulation of desire is a constant negotiation of fantasy, an exploration of the self through reaction to the other, then AI pornography and its self-referential imagery is more of an outsourced spank bank than porn as we know it. Sex has always been about the particulars: the stray hairs, the creases, the sweat, the folds. At the same time artificial pornography took off, Pornhub reported that the “reality” category increased 169 percent. Perhaps there is hope yet for the body, for our want of it and the bodies of sex workers who depend on sharing their image.

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, January 6, 2024 1:08 PM

Quote:
Originally posted by second:
“I haven’t found a technology yet that can do what I do,” says Evans. Since beginning her own management company, which handles communication and promotion for other performers, she has been screening chatbots and video services for herself and clients, but none quite stack up. Often, the most lucrative, and tedious, part of the job for self-employed content creators is responding to the thousands of chats and emails sent by fans—sorting through the spam, encouraging users to purchase original content, charging even to chat. Many management companies will outsource this labor to low-wage click workers overseas via sites like Upwork or Clickworker. Because Evans refuses to go down this rabbit hole (“It stinks of exploitation and corruption”), she manages her messages herself. Hypothetically, text generators like Botly, which profess to assist performers in scaling their business, should be an asset, but she hasn’t found technology that can strike the balance between flirting and running a business. For now, when users pay for Evans’s page, they’re getting the real deal.

Oh honey... if you thought hitting the wall when those wrinkle lines start showing up on your face was something to fear, you ain't seen nothing yet.

Nobody is going to be paying you anything in 10 years anyhow, but your entire "profession" is about to get a huge AI upgrade. Unless you're willing to actually go out and give dudes physical handies and blow jobs, none of you are going to have anything to offer in a strictly online "relationship" that technology isn't going to be able to do far better and far more efficiently.

And in the end, it will be the further degradation of society spurred on in large part by the extremely selfish, virtual, parasocial relationships you create online with lonely and desperate men that will be the jumping off point for a near-seamless transition into actual virtual relationships with actual virtual women. Women that will never need to eat, or sleep, or divide their infinite time between their customers. Women without an ego who are able and willing to do anything they've been programmed to do. Women that never need to shower. Women that never need to apply makeup. Women that will look perfect. Women that will never age. Women that will be able to change their outfits or hair color or even race with a snap of a finger. Hell... women that can just grow a cock at a moment's notice, if that's your thing.

You provide nothing, other than fantasy means of getting a man's rocks off when he's stupid and his monkey brain takes over, and if you're really good at your job you can pick just the right time to extract as much cash as possible out of them before the fantasy is over. And because there's absolutely nothing that remains after a cash exchange and a climax the only thing that is keeping you employed right now is that technology just hasn't progressed to the point to do it at your very low-effort baseline level.

The hubris to believe that you are in any way an irreplaceable and integral part of this equation is quite humorous. You're just keeping the bench warm for what's coming. And it doesn't even matter that the bench is going to be cold when the new lifeless women are sitting atop it. Because none of your customers ever got to feel the warmth of that bench or the body that provided the heat, and what you've been offering all this time was no more real than even the least convincing AI construct ever created in the first place.

Tick Tock

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Sunday, January 7, 2024 6:45 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

AI can turn mediocre writers into pretty good writers.

Kevin Drum / Jan 6, 2024 at 3:14 PM

In a paper published last summer, a pair of researchers looked at how well ChatGPT improves writing. They rounded up several hundred knowledge workers with average salaries around $70,000 and paid them to write short, typical business memo type things. After the first writing task, half the group was told to sign up for ChatGPT and use that to help out. https://www.science.org/doi/10.1126/science.adh2586

Here are the results:

With ChatGPT to help out, the time taken for the writing task decreased nearly 40%. When a human graded the writing, grades with ChatGPT increased about 20% on a scale of 1-7.

Roughly speaking, what happened was that bad writers became good writers and good writers became (slightly) better and (slightly) faster writers. Poor writers closed a big chunk of the original gap against good writers, though not all of it.

This doesn't mean that writers will be put out of work by ChatGPT. Not yet, anyway. But it does suggest that the pay premium for being a good writer is likely to go down. Why pay extra for a great writer when a mediocre writer can be made pretty good with a little bit of AI help?

https://jabberwocking.com/ai-can-turn-mediocre-writers-into-pretty-goo
d-writers/

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, January 12, 2024 2:34 PM

Virtual characters speak Japanese interact then play a virtual artificial character fighting in a virtual game and then react to 'English' comments

The 'Vtuber'

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Friday, January 12, 2024 8:35 PM

Quote:
Originally posted by second:
AI can turn mediocre writers into pretty good writers.

Kevin Drum

If Kevin Drum actually starts writing well, we know he's using.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, January 13, 2024 6:07 AM

Art and design – Is artificial intelligence capable of artistry?

https://www.teachwire.net/news/art-design-artificial-intelligence-arti
stry/#!

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, January 17, 2024 6:50 AM

AI trying to make scifi movies and Artificial Intelligence was watching Warhammer

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, January 20, 2024 12:11 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

M-M-M-M-MAX CREEPINESS —
These AI-generated news anchors are freaking me out

Channel 1's eerily real newscasters suggest a tumultuous future for online video.
By KYLE ORLAND - 12/15/2023, 9:57 AM

https://arstechnica.com/ai/2023/12/these-ai-generated-news-anchors-are
-freaking-me-out/

The world's first AI-generated news channel

Channel 1's AI news anchors. 100% AI Generated.

Channel 1 gives users a new more personal way to watch the news.
Introducing a new personalized global news network, powered by generative Al. Full launch in 2024.
https://www.channel1.ai/

AI network to launch on streaming by spring
The creators Mosam and film producer Scott Zabielski said they aim to launch Channel 1 AI for free with ad-supported streaming on apps this spring. The founders are also planning a Channel 1 app with its own translation feature by the summer.
https://www.usatoday.com/story/tech/news/2023/12/14/channel-1-ai-news/
71925360007/

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, February 13, 2024 4:10 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Feb 13, 2024

What if it improves to where it can do just about any task as well as we can do it, or better?

GPT-4, right now, can almost certainly pass most undergraduate math and science classes at top universities and possibly the humanities classes too (those might even be easier for GPT-4 than the science classes, but I’m much less confident about it). But it still struggles with, for example, the International Math Olympiad. How insane, that this is now where we have to place the bar!

Obvious question: how far will this sequence continue? There are certainly a least a few more orders of magnitude of compute before energy costs become prohibitive, and a few more orders of magnitude of training data before we run out of public Internet. Beyond that, it’s likely that continuing algorithmic advances will simulate the effect of more orders of magnitude of compute and data than however many we actually get.

So, where does this lead?

https://scottaaronson.blog/?p=7784

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, February 13, 2024 4:27 PM

Quote:
Originally posted by second:
There are certainly a least a few more orders of magnitude of compute before energy costs become prohibitive, and a few more orders of magnitude of training data before we run out of public Internet.

Reminds me of a commercial from the early 2000s.

He finished the internet?

Divorce this man immediately.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, February 13, 2024 5:08 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Quote:
Originally posted by 6ixStringJack:
Quote:
Originally posted by second:
There are certainly a least a few more orders of magnitude of compute before energy costs become prohibitive, and a few more orders of magnitude of training data before we run out of public Internet.

Reminds me of a commercial from the early 2000s.

He finished the internet?

Divorce this man immediately.

The A.I.s are being trained from the academic work written by Democrats, not from snide comments written by Trumptards who flunked out. Sure thing, 6ix, you quit, not flunked, because you already knew more than college professors.

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Tuesday, February 13, 2024 8:31 PM

Quote:
Originally posted by second:
Quote:
Originally posted by 6ixStringJack:
Quote:
Originally posted by second:
There are certainly a least a few more orders of magnitude of compute before energy costs become prohibitive, and a few more orders of magnitude of training data before we run out of public Internet.

Reminds me of a commercial from the early 2000s.

He finished the internet?

Divorce this man immediately.
The A.I.s are being trained from the academic work written by Democrats, not from snide comments written by Trumptards who flunked out.

You poor sweet summer child...

You think that you're going to have control of it?

Quote:
Sure thing, 6ix, you quit, not flunked, because you already knew more than college professors.

You know my relationship with money. Do you think there is a chance that I would just piss that away and flunk classes that I paid for?

Nah...

I could go back and finish my degree and I'd still have all those credits that I paid for.

Ain't no sense in that now. The fact that I don't have a degree puts me at the top of the hiring list in the 2020's. They know that my mind hasn't been fucked up by your people.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Wednesday, February 14, 2024 12:00 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Quote:
Originally posted by 6ixStringJack:
I could go back and finish my degree and I'd still have all those credits that I paid for. Ain't no sense in that now. The fact that I don't have a degree puts me at the top of the hiring list in the 2020's. They know that my mind hasn't been fucked up by your people.

Deep Fake
https://www.smbc-comics.com/comic/deepfake-2

"The really sad part is when they start deepfaking themselves for affirmation."

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Thursday, February 15, 2024 11:39 AM

You know all about that, goon.

Your deepfakes are all of your cats telling you what a great dude you are. You have no wife. You have no family. You have no friends.

Everybody hates you and you are a waste of carbon.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Sunday, February 18, 2024 7:22 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Eventually, life develops A.I., and then the A.I. takes over
https://www.smbc-comics.com/comic/meaningless

"Cosmos 4,982,112 was trash but 4,982,113 is going to get things perfect, I'm sure."

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, March 2, 2024 6:10 PM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

Waymo robotaxis can hit California highways after state approval

Sat, March 2, 2024 at 10:55 AM CST

California regulators on Friday granted Alphabet’s self-driving car division Waymo permission to expand its robotaxi service to include highways in several Bay Area cities and large swaths of Los Angeles, a massive expansion that comes amid concerns about the impact more driverless cars will have on city streets. The decision by the California Public Utilities Commission (CPUC) allows the company to deploy its robotaxis on local roads and freeways at speeds up to 65 mph.

https://www.yahoo.com/news/waymo-robotaxis-hit-california-highways-013
555172.html

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Saturday, March 2, 2024 8:02 PM

All it's going to take is one fiery auto wreck and a civilian dying and those things are going to be shelved for 20 years.

--------------------------------------------------

Political correctness is just tyranny, with a smiley face.

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Sunday, March 17, 2024 6:57 AM

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

The videos you are about to watch are not real.

They are generated from a text description.

Prompt: The camera directly faces colorful buildings in Burano Italy. An adorable Dalmatian looks through a window on a building on the ground floor. Many people are walking and cycling along the canal streets in front of the buildings.

Prompt: An adorable happy otter confidently stands on a surfboard wearing a yellow life jacket, riding along turquoise tropical waters near lush tropical islands, 3D digital render art style.

Prompt: This close-up shot of a chameleon showcases its striking color changing capabilities. The background is blurred, drawing attention to the animal's striking appearance.

Prompt: A corgi vlogging itself in tropical Maui.

Prompt: A white and orange tabby cat is seen happily darting through a dense garden as if chasing something. Its eyes are wide and happy as it jogs forward, scanning the branches, flowers, and leaves as it walks. The path is narrow as it makes its way between all the plants.

Prompt: Aerial view of Santorini during the blue hour, showcasing the stunning architecture of white Cycladic buildings with blue domes. The caldera views are breathtaking, and the lighting creates a beautiful, serene atmosphere.

Prompt: Tilt-shift of a construction site filled with workers, equipment, and heavy machinery.

Creating video from text https://openai.com/sora

Sora is an AI model that can create realistic and imaginative scenes from text instructions.

Read technical report: https://openai.com/research/video-generation-models-as-world-simulator
s

All videos on this page were generated directly by Sora without modification.

We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction.

Introducing Sora, our text-to-video model. Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt.

The Joss Whedon script for Serenity, where Wash lives, is Serenity-190pages.pdf at
https://www.mediafire.com/folder/1uwh75oa407q8/Firefly

NOTIFY: Y | REPLY | REPLY WITH QUOTE | TOP | HOME

Sunday, March 24, 2024 7:56 AM

Joscha Bach: “I am more afraid of lobotomized zombie AI guided by people who have been zombified by economic and political incentives than of conscious, lucid and sentient AI”

https://x.com/plinz/status/1771805114283479510

'Google Gemini Is Super Racist And Sexist,' Says Tesla And SpaceX CEO Elon Musk

https://www.freepressjournal.in/business/google-gemini-is-super-racist
-and-sexist-says-tesla-and-spacex-ceo-elon-musk

AI has come for music, but there’s still a Great Big Sea between people and algorithms
https://globalnews.ca/news/10332117/artificial-intelligence-in-music/
Suno is one of several companies building generative artificial intelligence software that allows users to create original songs using text prompts.

Ethical struggles of artificial intelligence

https://theridernews.com/ethical-struggles-of-artificial-intelligence/

NOTIFY: N | REPLY | REPLY WITH QUOTE | TOP | HOME

Sunday, March 24, 2024 10:48 AM