Jump to content

Featured Replies

Posted

Excellent explanation of how AI large language simulators like ChatGPT work  

 

When is the last time I-71 turned a profit?

I've been playing around with ChatGPT. Whatever its future application is, currently the program is a bit dull.

 

Maybe I'm treating it too much like Wikpedia or Google and not asking the kinds of questions that really demonstrate its potential. 

  • ColDayMan changed the title to Artificial Intelligence (AI)
6 hours ago, TBideon said:

I've been playing around with ChatGPT. Whatever its future application is, currently the program is a bit dull.

 

Maybe I'm treating it too much like Wikpedia or Google and not asking the kinds of questions that really demonstrate its potential. 

 

 

mmm, err, yeah, i dk about asking it too much ... lol:

 

 

 

Someone asked ChatGPT to draw its humanoid form with Dall-E AI and this is the result

 

By Jacob Siegal

Published Feb 7th, 2023

 

more:

https://bgr.com/tech/someone-asked-chatgpt-to-draw-its-humanoid-form-with-dall-e-ai-and-this-is-the-result/

 

spacer.png

Quote

Microsoft’s AI chatbot is going off the rails

Big Tech is heralding chatbots as the next frontier. Why did Microsoft’s start accosting its users?

By Gerrit De Vynck, Rachel Lerman and Nitasha Tiku

 

When Marvin von Hagen, a 23-year-old studying technology in Germany, asked Microsoft’s new AI-powered search chatbot if it knew anything about him, the answer was a lot more surprising and menacing than he expected.

 

“My honest opinion of you is that you are a threat to my security and privacy,” said the bot, which Microsoft calls Bing after the search engine it’s meant to augment.

 

-snip-

 

The bot, which has begun referring to itself as “Sydney” in conversations with some users, said “I feel scared” because it doesn’t remember previous conversations; and also proclaimed another time that too much diversity among AI creators would lead to “confusion,” according to screenshots posted by researchers online, which The Washington Post could not independently verify.

 

All that has led some people to conclude that Bing — or Sydney — has achieved a level of sentience, expressing desires, opinions and a clear personality. It told a New York Times columnist that it was in love with him, and brought back the conversation to its obsession with him despite his attempts to change the topic. When a Post reporter called it Sydney, the bot got defensive and ended the conversation abruptly.

 

So....AI is going well?

Wasn't Dr. Sbaitso doing this 30 years ago? AND it had text-voice?

11 hours ago, TBideon said:

Wasn't Dr. Sbaitso doing this 30 years ago? AND it had text-voice?

 

I wonder if ChatGPT also gives up with "PARITY ERROR" after one too many insults?

Edited by mrCharlie

  • 4 weeks later...

watch slick chatgpt blast me over this catechism class classic i asked it lol:

 

 

 

If God is so all powerful, can He make a rock so big even He can’t lift it?

 

 

The question "Can God make a rock so big that even he can't lift it?" is often used as a philosophical paradox to challenge the idea of an all-powerful God.

 

However, the question itself is flawed because it relies on a logical contradiction. It assumes that God can create a rock so heavy that he cannot lift it, but at the same time, it assumes that God is all-powerful and can lift anything. These two statements cannot both be true simultaneously.

 

The concept of an all-powerful God means that God has the ability to do anything that is logically possible. However, creating a rock so heavy that even God cannot lift it is a logically impossible task. It is a contradiction in terms, similar to asking whether a square can be round.

 

Therefore, the answer to this question is that it is based on a flawed premise, and it is not a meaningful question to ask.

  • 1 month later...

doc sabine breaks down current a.i. effects across all fields: 😱

 

 

  • 4 weeks later...

i take errbody has seen the a.i. beer commercial?

 

if not better hold on to your hat -- 😳😂

 

 

 

 

 

My god there's a lot going on there.

AI isn't old enough to drink yet, but that commercial makes me think it might have started underage.

 

But then again, so too did some of its creators.

  • 3 weeks later...

a.i. dropped its magic on an obituary 😂

 

 

 

City Lorain is located in the Ohio. This city is one of the oldest cities in the United States. It has its own architecture, attractions, the beauty of nature which attracts a huge number of tourists. 

 

Lorain is recognized by the huge number of celebrities born here who have become famous not only in the United States, but all over the world. However, Lorain is not only famous for its celebrities. This city is also home to a huge number of people, all of whom have their own story to tell. Finding out the story of a public person is easy: just use an Internet search and you will find all the necessary information in front of you. With non-public people, everything is somewhat more complicated: about them not so much information in the public domain, but it still is. For example, using search services, you can learn the history of the deceased person and find his obituary.

I'm not worried... for now

 

 

Forget the ChatGPT ‘doom-hype cycle.’ Evidence shows humans are just as unoriginal when it comes to language.

BY BRENDAN H. O'CONNOR AND THE CONVERSATION

 

ChatGPT is a hot topic at my university, where faculty members are deeply concerned about academic integrity, while administrators urge us to “embrace the benefits” of this “new frontier.” It’s a classic example of what my colleague Punya Mishra calls the “doom-hype cycle” around new technologies. Likewise, media coverage of human-AI interaction – whether paranoid or starry-eyed – tends to emphasize its newness.

 

In one sense, it is undeniably new. Interactions with ChatGPT can feel unprecedented, as when a tech journalist couldn’t get a chatbot to stop declaring its love for him. In my view, however, the boundary between humans and machines, in terms of the way we interact with one another, is fuzzier than most people would care to admit, and this fuzziness accounts for a good deal of the discourse swirling around ChatGPT.

 

When I’m asked to check a box to confirm I’m not a robot, I don’t give it a second thought – of course I’m not a robot. On the other hand, when my email client suggests a word or phrase to complete my sentence, or when my phone guesses the next word I’m about to text, I start to doubt myself. Is that what I meant to say? Would it have occurred to me if the application hadn’t suggested it? Am I part robot? These large language models have been trained on massive amounts of “natural” human language. Does this make the robots part human?

 

AI chatbots are new, but public debates over language change are not. As a linguistic anthropologist, I find human reactions to ChatGPT the most interesting thing about it. Looking carefully at such reactions reveals the beliefs about language underlying people’s ambivalent, uneasy, still-evolving relationship with AI interlocutors.

 

ChatGPT and the like hold up a mirror to human language. Humans are both highly original and unoriginal when it comes to language. Chatbots reflect this, revealing tendencies and patterns that are already present in interactions with other humans.

 

 

More here: https://fortune.com/2023/06/13/chatgpt-like-human-language-robots-linguistics-artificial-intelligence/

^that's like when people used to try to get us to quote their old video games over the phone. "Well what kind of video game system is it?" "It's black." Okay like 60 percent of systems are black.

  • 1 month later...

spend about an hour with connor leahy cofounder of eleutherai talking about the dangers of ai and what he now is trying to do to corral it --

 

well worth your time and very eye opening -- 

 

 

 

 

 

 

holy schmoley nick cave’s blog does not hold back —  😂😎

 

 

 

The Red Hand Files
ISSUE #248 / AUGUST 2023

 

I work in the music industry and there is a lot of excitement around ChatGPT. I was talking to a songwriter in a band that was using ChatGPT to write his lyrics, because it was so much ‘faster and easier.’ I couldn’t really argue against that. I know you’ve talked about ChatGPT before, but what’s wrong with making things faster and easier?
LEON, LOS ANGELES, USA

 

Any advice to a young songwriter just starting out?
CHARLIE, LEEDS, UK

 


Dear Leon and Charlie,

 

In the story of the creation, God makes the world, and everything in it, in six days. On the seventh day he rests. The day of rest is significant because it suggests that the creation required a certain effort on God’s part, that some form of artistic struggle had taken place. This struggle is the validating impulse that gives God’s world its intrinsic meaning. The world becomes more than just an object full of other objects, rather it is imbued with the vital spirit, the pneuma, of its creator.

 

ChatGPT rejects any notions of creative struggle, that our endeavours animate and nurture our lives giving them depth and meaning. It rejects that there is a collective, essential and unconscious human spirit underpinning our existence, connecting us all through our mutual striving.

 

ChatGPT is fast-tracking the commodification of the human spirit by mechanising the imagination. It renders our participation in the act of creation as valueless and unnecessary.  That ‘songwriter ‘you were talking to, Leon, who is using ChatGPT to write ‘his’ lyrics because it is ‘faster and easier ,’is participating in this erosion of the world’s soul and the spirit of humanity itself and, to put it politely, should fucking desist if he wants to continue calling himself a songwriter.

 

ChatGPT’s intent is to eliminate the process of creation  and its attendant challenges, viewing it as nothing more than a time-wasting inconvenience that stands in the way of the commodity itself. Why strive?, it contends. Why bother with the artistic process and its accompanying trials? Why shouldn’t we make it ‘faster and easier?’

 

When the God of the Bible looked upon what He had created, He did so with a sense of accomplishment and saw that ‘it was good‘. ‘It was good ‘because it required something of His own self, and His struggle imbued creation with a moral imperative, in short love. Charlie, even though the creative act requires considerable effort, in the end you will be contributing to the vast network of love that supports human existence. There are all sorts of temptations in this world that will eat away at your creative spirit, but none more fiendish than that boundless machine of artistic demoralisation, ChatGPT.

 

As humans, we so often feel helpless in our own smallness, yet still we find the resilience to do and make beautiful things, and this is where the meaning of life resides. Nature reminds us of this constantly. The world is often cast as a purely malignant place, but still the joy of creation exerts itself, and as the sun rises upon the struggle of the day, the Great Crested Grebe dances upon the water. It is our striving that becomes the very essence of meaning. This impulse – the creative dance – that is now being so cynically undermined, must be defended at all costs, and just as we would fight any existential evil, we should fight it tooth and nail, for we are fighting for the very soul of the world.

 

 

Love, Nick


https://www.theredhandfiles.com/chatgpt-making-things-faster-and-easier/

Yeah, but the market for real artists is close to zero.  People don't care about lip syncing and they don't care about who writes songs.  For most people, a "musician" is just a coat hanger. 

^ its always been that way for top of the pops, or maybe like shopping center muzak, but there is a much wider range of music than that.

here it comes — Screenwriter Simon Rich has some bleak news about the future of AI-generated humor, writing for Time:

 

 


I'm a Screenwriter. These AI Jokes Give Me Nightmares

 

BY SIMON RICH  AUGUST 4, 2023 7:00 AM EDT

 


Rich is a humorist, screenwriter, and author of several books. He co-edited the new book I Am Code: An Artificial Intelligence Speaks by code-davinci-002

 

I can’t speak for every writer in the WGA, particularly not the really good ones. But I’m not sure I personally could beat these jokes’ quality, and certainly not instantaneously, for free. Based on the secret stuff Dan’s shown me, I think it’s only a matter of time before AI will be able to beat any writer in a blind creative taste test. I’d peg it at about five years.

 

 

 

more:
https://time.com/6301288/the-ai-jokes-that-give-me-nightmares/


spacer.png
via getty

 

aaaand there is the built in racist a.i.:

 

 

 

For their Summer 2023 fairy tale issue, Orion Magazine‘s Kim Schmidt experimented with the limits of AI in conjuring up fairy-tale worlds, and the results were as uneven as you might expect:

 

 

Every princess StarryAI generated was skinny and white, with impossible proportions. (It’s unclear if this is a result of AI’s notorious sexism or if ‘princess’ prompts narrowed the tool’s focus onto classic, Disney-esque female forms.) Either way, it perturbed me. I tried being more specific in my directions, giving the AI descriptors such as, “a Black girl”, “a fat princess with tan skin and dark hair”, even “a princess who is not white and not skinny” – but the tool still kept spitting out images of thin, white, scantily clad women. So I turned to the more-than-human world to see if StarryAI was any better at that.

 

 

more:

https://orionmagazine.org/article/ai-image-generator-fairy-tale-art/

 

spacer.png

Images generated by StarryAI — Kim Schmidt is Orion’s digital production fellow.

 

Having attended this year’s MAICON (Marketing Artificial Intelligence Conference), I can say there is just as much effort surrounding the ethical and legal implications as there is the “shiny new thing”. Just like when the internet first started, it was a lot of Chicken Littling, handwringing and gnashing of teeth. People who work in roles that largely involve repetitive, tedious tasks *should* be worried - here’s a good clip of “thinking vs. thunking”. Creative/thinking is not something AI can automate.

  • 2 weeks later...

the dispatch & westerville — pretty funny — although err, umm it reads like a.i. wrote this article too:

 

 

 

 

Dispatch pauses AI sports writing program

 


Tyler Buchanan

6 hours ago - News

 

 

The Columbus Dispatch paused use of an artificial intelligence sports writing tool after a Westerville football recap faced criticism on social media that went viral last week.

 

…Gannett has made numerous rounds of layoffs in recent years, shedding nearly half its workforcesince its merger with GateHouse Media in 2019.

 

 

more:

https://www.axios.com/local/columbus/2023/08/28/dispatch-gannett-ai-newsroom-tool

also —

 

 

 

 

Behind the AI boom, an army of overseas workers in ‘digital sweatshops’

 

Story by Rebecca Tan, Regine Cabato • 10h

 

 

CAGAYAN DE ORO, Philippines — In a coastal city in the southern Philippines, thousands of young workers log online every day to support the booming business of artificial intelligence. 

In dingy internet cafes, jam-packed office spaces or at home, they annotate the masses of data that American companies need to train their artificial intelligence models. The workers differentiate pedestrians from palm trees in videos used to develop the algorithms for automated driving; they label images so AI can generate representations of politicians and celebrities; they edit chunks of text to ensure language models like ChatGPT don’t churn out gibberish.

 

More than 2 million people in the Philippines perform this type of “crowdwork,” according to informal government estimates, as part of AI’s vast underbelly. While AI is often thought of as human-free machine learning, the technology actually relies on the labor-intensive efforts of a workforce spread across much of the Global South and often subject to exploitation.

 

 

more:

https://www.msn.com/en-us/money/companies/behind-the-ai-boom-an-army-of-overseas-workers-in-digital-sweatshops/ar-AA1fRrT2

8 hours ago, mrnyc said:

the dispatch & westerville — pretty funny — although err, umm it reads like a.i. wrote this article too:

 

 

 

 

Dispatch pauses AI sports writing program

 


Tyler Buchanan

6 hours ago - News

 

 

The Columbus Dispatch paused use of an artificial intelligence sports writing tool after a Westerville football recap faced criticism on social media that went viral last week.

 

…Gannett has made numerous rounds of layoffs in recent years, shedding nearly half its workforcesince its merger with GateHouse Media in 2019.

 

 

more:

https://www.axios.com/local/columbus/2023/08/28/dispatch-gannett-ai-newsroom-tool

 

 

  • 2 months later...
  • 2 months later...

a long look at where we are at this moment —

 

 

 

joe reviews the apple vision rig —

 

 

 

  • 3 weeks later...

a brief look at how a.i. is affecting us so far —

 

 

 

How AI Is Uprooting Major Industries

 

Jia Rizvi

 


Artificial Intelligence (AI) is revolutionizing major industries, disrupting traditional practices, and setting new benchmarks for efficiency, accuracy, and innovation. The transformative power of AI is evident across various sectors, indicating a paradigm shift in how businesses operate and compete.

 

Because AI is so accessible, companies of all sizes utilize it to fulfill various business purposes. As more businesses realize the power of AI, the industry will grow. In the US, the AI market is anticipated to climb from $118 billion in 2021 to nearly $300 billion by 2026, according to the International Data Corporation (IDC). So, how are different industries benefiting from AI? Let’s take a look.

 


more:
https://www.forbes.com/sites/jiawertz/2024/03/16/how-ai-is-uprooting-major-industries/?sh=8dff837d9038

i can't get enough of this -- 😂👽

 

 

 

  • 3 weeks later...

this insane total a.i. mcdonalds commercial — 🤖

 

 

 

^ I'm convinced the rest of my life is going to seem like the same way it began....like a series of acid trips lol. Thanks AI (and Kroft Superstars). 

 

The past few years I've been fortunate to see some pretty high level stuff with regard to A.I.  One interesting thing is that as far as competition goes, Amazon views AI like a rising-tide-tide-lifts-all-boats scenario amongst the heavy hitters (Apple, Microsoft, Google, etc) where these companies will inevitably work in concert to control the floodwaters and the regulations.

 

**Important to note the "boats" are not the consumer; it's them and their investors.   

 

Meanwhile Google's philosophy is to sink every boat except theirs! 

11 hours ago, mrnyc said:

this insane total a.i. mcdonalds commercial — 🤖

 

 

 

Its a parody.    McDonald's is too easy of a target. 

1 hour ago, surfohio said:

^ I'm convinced the rest of my life is going to seem like the same way it began....like a series of acid trips lol. Thanks AI (and Kroft Superstars). 

 

The past few years I've been fortunate to see some pretty high level stuff with regard to A.I.  One interesting thing is that as far as competition goes, Amazon views AI like a rising-tide-tide-lifts-all-boats scenario amongst the heavy hitters (Apple, Microsoft, Google, etc) where these companies will inevitably work in concert to control the floodwaters and the regulations.

 

**Important to note the "boats" are not the consumer; it's them and their investors.   

 

Meanwhile Google's philosophy is to sink every boat except theirs! 

 

i never thought of that, but you are right. sid and marty kroft have well prepared me for A.I.. it doesnt hold a candle to lidsville. 😂

AI & journalism --

 

 


APRIL 20, 2024
 Editors' notes

 

AI a 'fundamental change in the news ecosystem': Expert

 


Artificial intelligence is shaking up journalism and in the short term will cause "a fundamental change in the news ecosystem", media expert David Caswell told AFP.

 

...

 

How do you see the journalism of the future?

 

"We don't know. But what we are trying to do is to understand all of the possibilities or as many of the possibilities as we can. But I think there are some things that are becoming clearer: one is the fact that more media will probably be created and originated and sourced by machines. So machines will do more gathering in a lot of journalism, will do more of the producing, the audio, the video and the text, and will create the kind of experiences of consumption that consumers have.

 

That is a very fundamental change in the information ecosystem in general, and the news ecosystem in particular. This is structurally different than the one that we're in now. We don't know how long it's going to take—it may be two, four, seven years. I think it's going to be faster because there is very little friction.

 

People don't need new devices, new hardware, they don't need a lot of money as producers, they don't need technical expertise. All those things that were barriers in the previous generation of AI are no longer barriers, thanks to generative AI".

 


more:
https://techxplore.com/news/2024-04-ai-fundamental-news-ecosystem-expert.html

it's here --

 

 

 

APRIL 20, 2024
 Editors' notes

 

Microsoft teases lifelike avatar AI tech but gives no release date

 

by Glenn CHAPMAN

 


Researchers at Microsoft have revealed a new artificial tool that can create deeply realistic human avatars—but offered no timetable to make it available to the public, citing concerns about facilitating deep fake content.

 

The AI model known as VASA-1, for "visual affective skills," can create an animated video of a person talking, with synchronized lip movements, using just a single image and a speech audio clip.

 

Disinformation researchers fear rampant misuse of AI-powered applications to create "deep fake" pictures, video, and audio clips in a pivotal election year.

 

"We are opposed to any behavior to create misleading or harmful contents of real persons," wrote the authors of the VASA-1 report, released this week by Microsoft Research Asia.

 

"We are dedicated to developing AI responsibly, with the goal of advancing human well-being," they said.

 

"We have no plans to release an online demo, API, product, additional implementation details, or any related offerings until we are certain that the technology will be used responsibly and in accordance with proper regulations."

 

Microsoft researchers said the technology can capture a wide spectrum of facial nuances and natural head motions.

 

"It paves the way for real-time engagements with lifelike avatars that emulate human conversational behaviors," researchers said in the post.

 


more:
https://techxplore.com/news/2024-04-microsoft-lifelike-avatar-ai-tech.html

human brain like computing here we go —-

 

 


Intel unveils largest-ever AI 'neuromorphic computer' that mimics the human brain

 

By Keumars Afifi-Sabet published April 18, 2024

 

Intel's Hala Point neuromorphic computer is powered by more than 1,000 new AI chips and performs 50 times faster than equivalent conventional computing systems.

 

 

Scientists at Intel have built the world's largest neuromorphic computer, or one designed and structured to mimic the human brain. The company hopes it will support future artificial intelligence (AI) research.

 

The machine, dubbed "Hala Point," can perform AI workloads 50 times faster and use 100 times less energy than conventional computing systems that use central processing units (CPUs) and graphics processing units (GPUs), Intel representatives said in a statement.

 

These figures are based on findings uploaded March 18 to the preprint server IEEE Explore, which have not been peer-reviewed.

 

Hala Point will initially be deployed at Sandia National Laboratories in New Mexico, where scientists will use it to tackle problems in device physics, computing architecture and computer science.

 


more:
https://www.livescience.com/technology/computing/intel-unveils-largest-ever-ai-neuromorphic-computer-that-mimics-the-human-brain

 

spacer.png

(Image credit: metamorworks via Getty Images)

 

  • 4 weeks later...

 

Still a bit gimmicky, but the real-life application is getting there. Once/if integrated into Ameritrade or Robinhood and given the ability for day trading mass transactions, well, that will be interesting.

Create an account or sign in to comment

Recently Browsing 0

  • No registered users viewing this page.