Why OpenAI’s ChatGPT Is Such A Big Deal
HTML-код
- Опубликовано: 23 июл 2024
- OpenAI, which Elon Musk helped to co-found back in 2015, is the San Francisco-based startup that created ChatGPT. The company opened ChatGPT up for public testing in November 2022. In under a week, the artificial intelligence model amassed over a million users, according to OpenAI’s CEO, Sam Altman. By the end of January, ChatGPT was averaging about 13 million visitors per day. Users have had ChatGPT write everything from essays, to lyrics and even correct computer code. ChatGPT is part of a growing field of AI known as generative AI, which allows users to create brand new content including videos, music and text. But generative AI still faces a number of challenges, such as developing content that is inaccurate, biased or inappropriate. Now enterprises and the public are wondering what wide access to AI will mean for businesses and society.
Chapters:
00:00 - Intro
01:36 - Chatting with ChatGPT
03:03 - Understanding ChatGPT
06:39 - Use cases and limitations
10:09 - Future implications
Credits:
Produced by: Magdalena Petrova
Edited by: Dain Evans
Additional Camera: Andrew Evers, Sydney Boyo
Supervising Producer: Jeniece Pettitt
Editorial Support: Jonathan Vanian, Jennifer Elias
Graphics: Mallory Brangan
» Subscribe to CNBC: cnb.cx/SubscribeCNBC
» Subscribe to CNBC TV: cnb.cx/SubscribeCNBCtelevision
About CNBC: From 'Wall Street' to 'Main Street' to award winning original documentaries and Reality TV series, CNBC has you covered. Experience special sneak peeks of your favorite shows, exclusive video and more.
Connect with CNBC News Online
Get the latest news: www.cnbc.com/
Follow CNBC on LinkedIn: cnb.cx/LinkedInCNBC
Follow CNBC News on Facebook: cnb.cx/LikeCNBC
Follow CNBC News on Twitter: cnb.cx/FollowCNBC
Follow CNBC News on Instagram: cnb.cx/InstagramCNBC
#CNBC
Why OpenAI’s ChatGPT Is Such A Big Deal
One of the greatest features of ChatGPT is that you can give it a complex task, then just mention a tiny change in the overall approach to the problem, and watch it redo the whole task just from that short prompt. It's so much better than having to work out how to reword the whole instruction.
Can you give an example? This sounds interesting
@@MrAryanthaker
U: Write me an intro that I can share on my LinkedIn
CHAT:
U: Seems too long. Can you make it shorter?
CHAT:
U: Make it sound more fun and light-hearted
CHAT:
U: AI
@@MrAryanthaker it basically remembers the context of the conversation, so it's feels like you're ping-ponging ideas in a organic way
@@MrAryanthaker I agree. I was asking it about a fitness routine and asked “what if we add …?” It took my suggestion and reworked the routine. I didn’t have to remind it of the topic at hand. I can even return to a topic days later within the same chat. I can ask “do you remember I’m trying to (bla bla)” and it would reply affirmatively. It’s an interesting technology.
You can make it create text based games. It'll basically write a novel where you're the protagonist. I'm currently in a game where I'm a 15th century king. It generated an entire royal court of characters and advisors and I can ask it to go anywhere or do anything and it'll generate story of me doing it. Now, whats really cool is that if I want to change a characters name or the overall rules of the game it'll do it and I wont have to restate the original rules of the game. It understands context and subtlty
"The worn that ate guacamole" - By ChatGPT
There once was a worm so plump and so fair,
Who lived in a garden with flowers everywhere.
He'd nibble on roots and leaves all day,
But one day, he found something new to play.
He crawled to a bowl, filled with green and brown,
And took one bite, then tumbled down.
It was a delight, it was so good,
He ate and ate, like he knew he should.
He ate guacamole, with chips so crisp,
And when he was done, gave a little flip.
He said to himself, "This is heaven on earth,"
And danced with glee, for all he was worth.
The worm was so happy, his heart felt light,
He'd never tasted anything quite so bright.
He hummed a tune, and twirled with glee,
He was the happiest worm, you'll ever see.
So if you see a worm, wiggling with delight,
And you hear a hum, in the garden at night,
Just know that he's found, his favorite treat,
A worm that ate guacamole... ain't that sweet?
"This is not something that is going to take your job. This is a novelty, this is a gimmick."
-cnbc technology reporter
Something tells me this statement will age poorly
Lol it doesn’t even need to age it was a statement that came out wrinkled with a foot in the grave 😂
@@danielrosenberg6085 😂😂 for sure
@ghost mall if you want a good laugh check out ex-Microsoft CEO Steve Ballmer’s reaction to the iPhone in 2007
A lot of white collar jobs just consist in creating reports and making summaries. Most of them will disapear witithin a few years.
@@sisibibi3282 Amassing information, filtering signal from noise and reducing it to key points in the form of a report isn’t trivial work for human beings, even if it is something that can be automated in part with today’s tech. I agree there will likely be a shift, but I’d warn against using words like “just” to describe these kinds of tasks. Doing so implies that these people never contributed meaningfully, and for some people it’s a slippery slope from there to saying “they’ll get what they deserve” if and when they’re out of a job or out on the street.
I’ve been using it to play around with and oh my god is it revolutionary. I’m in nursing school rn and we have to write these annoying careplans that actual nurses never have to do and I asked it a very vague and open ended question with some information and it gave me an actual valid and correct diagnosis and the way it worded it sounded like it came straight out of my pen. Something that would take 30mins to an hr for me to do took it less than 10 seconds
This is what i'm talking about. People think AI will take their jobs, but AI needs humans to ask the questions in the first place. And it's not like it can get up and do the labor either.
All i have to say is skynet
Software dev here, you did a really great job summarizing the last few months of AI progress and thoughts on where it is headed. Well done! 👍
Oh sure, "Software developer", (exactly what you'd expect an generative A.I. program to say..)
Yep. And soon we will be talking about the last few days of AI progress then the last few hours.
GPT is a SCAM to stop you from getting multiple search results
You will get the GOVERNMENT SEARCH RESPONSE - And you will be happy
Can I borrow like 200 bucks?😃
@@bluethunder9102 yes
I can't belive i am going to say this, but CNBC has been publishing some high quality content in the past year. Hopefully this continues.
agreed
True!!
They use ChatGPT to write scripts & content for their videos 😂
@@ahmadhafis4 lol that would be funny
the fun thing is, it's true now i a lot of worklpaces.
We truly are entering a stage of technological renaissance
We’ve been in one since 1930s
@@damckissen I hope Ai takes your job and makes you starve!
@@damckissen it won't. The law will catch up and block AI doing creative pursuits
@@damckissen Well generative AI is useless without human imagination powering it. You still need to come up with the idea, it's just that your computer can now take care of the actual implementation.
A slowly boiling frog comes to mind for some reason. 🤔
This iteration of ChatGPT will not take your job, but the improvement of these generative AI is a threat to a lot of jobs. Companies fight to be competitive, so when one company is seeing positive results using AI, it naturally forces other companies to adopt the new technology.
Absolutely, News report writing, financial analysis, coding, customer care and many other professions are on their way out in the next 5 to 10 years.
It will only accelerate from here.
For lazy, entitled individuals, AI is a threat. To those with initiative and a bit of entrepreneurial spirit, it is a great opportunity.
@@marcogentle A.I will take away all the creative jobs and then take away customer service. It’s then take away a huge chunk of analyst/consultant and coding jobs. It’s won’t erase it, but only the top of the feild will survive.
AI will not take your job away, this fear mongering always goes around when new technology comes out. If they take jobs away, how are these big corporations going to make money? You cant make money if there are no consumers with money. Eventually that would collapse the economy. The AI will probably be used as a tool for humans to make them more productive.
I used this tool and it's insanely scary how advanced it is. It can write stories, songs, can do complex math analysis. AI will do to white collar jobs, what machines have done to blue collar jobs during the machine age.
No way, not with the why that it plagiarizes and hallucinates fake references and data. I cannot use this for my job. Google never released their LLM “AI” due to their concerns over these things.
Theron lies the problem, and a rather substantial problem. In fact, multiple problems. What do people do then?
@@johnraviella6561 What do humans really do unless they are extremely creative? Everyone paraphrases and copies. No one wants to admit it.
@@alb12345672 yes true, but you can’t plagiarize in a commercial setting. You certainly can’t have it write a paper that cites references which don’t exist. I can’t use it in my job. SciGEN out of MIT has been around for decades. This is more sophisticated but the concept is the same, this isn’t anything particularly new
@@johnraviella6561 It's going to be combined with wolframalpha soon, so that'll be a none issue.
But even beyond your particular use case, there are so many uses that Chatgpt could save a person time on.
E.g.
1.Quickly generating text, such as emails, reports or social media posts.
2.Answering frequently asked questions in customer service.
3.Providing definitions and explanations of terms, concepts and ideas.
4.Translating text to and from different languages.
5.Summarizing lengthy documents or articles.
6.Providing recommendations and suggestions based on a person's preferences.
7.Generating creative ideas and content.
8.Solving mathematical problems and generating formulas, it's getting better here.
9.Generating code snippets and programming solutions.
10.Answering trivia questions and providing general knowledge information
I recently had it put together an itinerary for me, something that would have taken me many hours and lots of stress, was done in 35 seconds.
Everyone is fixated on what it can't do, but I doubt that it can't save any user at least some time.
ChatGPT is like a desktop computer in the 1990s, it's cool and it it's helpful in many situations but it's not yet essential. In about 5-10 years though, it will be absolutely essential and people will wonder how we ever lived without it. Furthermore, I think that an AI first company will become the richest most powerful company in the world. (Microsoft has a real shot at being king in the next 2 decades)
chatgpt teaches me better than some of my teachers lol
There's no way that Microsoft apple will let another company take their spot. Chip companies have a better chance of taking over
@@gsdblack1 Chip manufacturers work with silicon (usually) in itself totally incapable of doing AI.. It takes software to implement “intelligence” so that is where the software companies are going to dominate.
More like 2 years. This thing is getting exponentially better every 6 months.
Will it also run on an MS-DOS core?
OpenAI's ChatGPT is a true marvel of modern AI technology, revolutionizing the way we interact and communicate with computers. Its advanced natural language processing capabilities, combined with its massive training data, allow for unprecedented levels of human-like conversation, blurring the lines between man and machine. It is a testament to the power of deep learning algorithms and the dedication of OpenAI's team to push the boundaries of what is possible. ChatGPT represents a pivotal moment in the history of AI and will undoubtedly have a profound impact on our daily lives and the future of technology as a whole. It is truly a big deal.
11:05 Chat GPT literally makes it impossible to tell if a student wrote their essay or thesis. It’s fundamentally shaking up the entire educational landscape - forever - and you call it a GIMMICK???
Let’s not even begin on the artists freaking out because AI art is replacing them as we speak.
Somebody is in denial about their job being taken by AI.
They're trying to keep the panic down, this is what mainstream media does.
Behind the curve and increasingly wrong.
were going into a recession and people that wouldn’t be replaced will for someone who charges less, gunna get crazy real quick. But hey id be happy to have technology and a farm community, honestly i love both
ChatGPT is a toy and nothing more. Anyone who calls it AI and says it is going to replace writers or whatever is trying to get you to invest in something. I have about $183,000 in life savings that I want to invest, but it's difficult for me to bite the bullet and do it.
ChatGPT will summarize the key strength of a company, saving you hours of research on the value of the company. This is just the tip of the iceberg of what you can do with AI to invest better. I will suggest you seek a financial advisor to guide you on how to invest your lifesavings though.
@@glenbert1396 you are right; it is always advisable to speak with financial counselors. Since I was doing so poorly at initially, I didn't feel very satisfied with my gains in comparison to my prior results. I decided I needed to diversify into stronger assets, so I contacted an investment advisor. I made a net profit of $650k in that same year, which is around 50 times more than I typically do.
@@anthonyrussell5718 That's actually quite impressive!! I could use some Info on your investment adviser, I am looking to make a change on my finances this year as well.
@@roseroland1998 I have "LISA ELLEN SHAW" as my investment advisor. She has a solid reputation in her field and is a true genius when it comes to diversified portfolios, which help portfolios be less vulnerable to market downturns. She may be a name you are already familiar with; a Newsweek piece helped me to do so. She's a Google-able person.
@@anthonyrussell5718 I am so glad i stumbled upon this conversation. Lisa seems to really know her stuff. I searched the web for her using her full name and found her page, read her resume, education, qualifications and it was really impressive. She is a fiduciary who will act in my best interest. So I booked a session with her. I appreciate!!
That "interview" was eerie!! I have been aware of ChatGPT and what it does, but had not paid too much attention until now. Thanks for the excellent and informative video. This is an interesting technological stepping stone, clearly still in its nascent stages. Can't wait to see what it develops into, or what other technologies this could enhance in a couple decades.
I highly recommend you sit down and talk to it.
I personally use it to study. It’s better than most of the human teachers I’ve had at explaining highly complex topics in a simple and understandable way.
Any questions you have about the future of AI, it’ll answer it. Or better yet, it’ll help you think through it yourself and it’ll tell you if your thoughts are logical or not.
Lies again? Hello OCP
This comment and channel looks like a bot!!!
Try it yourself, but since this videos over-exaggerates a lot of things, don't expect it to speak. ChatGPT just outputs a bunch of text and expects you to enter some text.
@@THEHIPP0 Oh yeah, I definitely did catch that they ran the text output through a text to speech engine to add a bit of "realism". It was a good (and eerie) effect!
For me the biggest take away re the current version of ChatGPT is that in the weeks and months (not years) ahead: everything we currently know about this technology will be archaic.
I've heard that last december, not much has changed.
GPT-4 will launch this year and is set to have 100 trillion parameters compared the current 175 bilion even if it's an overestimated projection it will be much more optimized and have quicker response times.
@@autisticphaglosophy7128 it's scary to imagine. how much energy will it consume
@@autisticphaglosophy7128 the CEO of OpenAI said that's BS.
@@autisticphaglosophy7128 The CEO of OpenAI himself has said that people are seriously overestimating how capable and improved GPT-4 will be, it won't have nearly so many parameters, since the electricity alone to power answers from such a large model would be in the single digit *dollars* (not cents !) per answer, let alone train it.
This shines at allowing me to bounce ideas off it and give me a starting point on how to tackle a problem.
I used it as one of the sources for fixing IT issues. While it's instructions never produced any complete solutions so far but some suggestions were worth exploring that I hadn't thought about or was thinking about but needed a final push to go explore that possibility.
Also, the art isn't in the information it can provide, but in the right (series of) question to ask it to get the most informative answer. So it still requires you to understand the subject in order to ask the right question and get a somewhat informative answer.
ChatGPT is amazing in organizing data though, it can pull up info from multiple sources that would take hours to manually collect and organize.
A colossal omission in this story are the different levels of "pay-to-play" API that are available. GPT-3 Lite was trained on 20 billion "parameters" while GPT XL was trained using 350 billion... What big $$ companies will be using soon is not what the general public has been exposed to.
Good lawd!
@@thatisabsolutelykooooge2211 don't believe anything you read.
This will play into the hands of all those data mining and identity theft operations that glean personal data and now re-purpose it for who-knows-what.
@@bernardusmuller1109 words to live by. As Poe said, 'Believe nothing you hear, and only one half that you see.'
This is one of the biggest advancements in knowledge work ever. It's up there with computers and the internet itself.
No. Its a chatbot. It doesn't come close to computers or the internet.
Well in the particular case of the Chatbot it does not create knowledge it only uses what already exists.
@@kayakexcursions5570 You're incredibly naive and ignorant if you think it's "just a chatbot".
@Zavil I can program neural networks, you're just an idiot. Its a chatbot plain and simple. There's companies paying programmers to use it for email marketing.
@@kayakexcursions5570 Naive and ignorant it is.
Whoever thinks that generative AI is just a novelty or won't take a lot of people's job is widely mistaken. As someone that works in the software development field, people's jobs are threatened by the advancement of future iterations of chatGPT. Programmers, writers, artists, etc. can all eventually replaced by future updates to systems like these. It's not an "if", it's a "when".
Although my job will be threatened, I welcome the advancement. Now is the time to find out how you can use it to your advantage before you get left behind. It's only a matter of time.
What will happen to all those that will be “left behind” as you mention? Starvation? Now is the time for governments to act before the music stops and there are no chairs left.
If you can use it for your advantage, your competitors can also use it to their advantage. Nobody is actually going to come ahead from this, other than the AI companies
@@jimmyz2684 there's plenty of companies that are going to come out ahead of AI. I never said that a whole occupation will be eliminated from existence, but I guarantee you that when this starts to get utilized more heavily in the future and is upgraded over time, companies will not need as many people as they do now. Instead of hiring 20 devs, they may hire 15. Instead of 40 accountants, they may hire 18 for high value accounts and another 10 to review the output of the AI.
It will make people more efficient at their jobs and therefore will increase output of a single person which in turn reduces the amount of headcount needed.
"The Internet is a fad, it will go away. " - most people ~25 years ago.
AI is the next step in human evolution. It's inevitable.
It will replace some jobs but artists? Never. I don't just want good content, I want to know that there is vulnerable human behind of it who opens up their soul for us. ChatGPT might be good for design and non fictional books though.
I was writing code in 1968. I was also in college. I tutored other students. Now, when I look back, I think of myself as a human ChatGBT helping them get the right answers without having to do the work. Back then I was rather naive. I thought the internet had been developed to allow researchers to communicate knowledge. Who knew it would become what it is today.
Incredible really. Imagine what another 50 years will bring.
Back then, if students had cracked a history book on the abuses of human morals, it would have given good clues about where the internet would gravitate. Creating AI the lazy way by letting it learn from all the crap on the internet is sheer foolishness that will come back and bite us hard. An example: Elon Musk allowing his AI to comprehend all live traffic situations encountered by all his cars now on the road. That sounds like a good idea, but here we are years later, and there is still no true self-driving that any legislature would ever pass. And, as always, the human factor is sprinkled with politics. Elon's self-driving cars could be responsible for a thousand deaths a year, while the humans driving cars are accountable for that number by the hour.
Many have speculated that Microsoft will use ChatGPT in Bing, but few have talked about OpenAI CEO Sam Altmen's proposal. Because the best neural networks require so much data and computing power, many smaller businesses can't afford it. So Sam has suggested that a large company is responsible for the heavy and basic learning, in law, medicine, physics, etc., then sell the learned software to companies that make some small changes according to their needs.
Edit: Although there are technological breakthroughs in OpenAI's ChatGPT, you get the feeling from the media reporting that expectations are growing faster than the technology itself.
Concentrating the basic functions of business and law in the hands of a single corporation. What could possibly go wrong?
This has to be the best thing to happen since the search engine.
Since sliced bread, even.
Nope not when it can sensor you according to its opinions based on people who wrote the code chat GPT. Be afraid of it
@@gilberttorres8 Google sensors search results all the time. Bias is a fact of life, and its reach encompasses and always has encompassed the technology that you and I use everyday.
@@koshobai They just want racist and pornographic content.
@@gilberttorres8 You must have failed grade school. The word is "censoring." Search engines and mainstream media has been censoring topics and people since the dawn of time.
Interviewing the AI was very creative. Loved it :D
I was using this with my girlfriend for "academic" purposes for an online course.
It's both amazing and scary at the same time.
Really feel like this is a turning point.
Right there with you. It helped me pass with flying colors.
Your girlfriend did not have any relative importance to this topic
@@sunablast right
@@sunablast it was a course she was doing for university/college, not myself. Hence why I didn't say it was me. We were blown away with how good it was. Not sure why it bothers you 😂
By the way, it was a pass!
I think it is extremely naive and dangerous to assume Open AI and massive companies like Microsoft that are investing in it are doing so for the benefit of all of humanity. It is just like how any company will emphasise their CSR or philanthropic endeavours (which themselves should not be taken at face value, i.e. greenwashing) to placate or distract entirely from public concerns about their dubious business practices as they grow and increasingly gain market power. There will be winners and losers in this and those who control its capital will be the ones to determine how it is used. Right now they are at the stage of trying to keep the alarm bells from going off. Unfortunately, our government here in the US seems to fail at enforcing even the most basic regulations. It is hard to imagine that we'll get ahead of this before massive job loss and even more extreme market consolidation.
Couldn't have said it better. Most people are so awestruck by the shiny, new toy that they glaze over the ethics of stealing content (art, writing, etc.) in order to make the original creators of this content irrelevant. Humanity will likely never understand the concept of enough. I believe we've reached the stage where technological "advancement" significantly contributes to intellectual decline in humans. (For example, is it really better to read and trust a synthesized review that tells you what to think than to sift through several reviews and arrive at your own conclusions?) The irony is that the same big tech CEOs that push these kinds of shortcuts to thinking onto the masses often drastically limit their own children's use of technology.
Exactly, anything that involves (bad) humans will be corrupted in some way lol. The whole concept seems sketchy. I think they'll start trashing the standard search engines and replace it with this. That way, they can control what people see with this 'one answer' system. I would love to do a study on this. Seems like it removes our ability to research and find information from various sources.
Legislators have let us down. They should have not allowed OpenAI to release this nuclear bomb on an unprepared society.
Well said. I really wished big tech and governments had tried harder to address problems such as poverty, food shortage, and healthcare inequality rather than creating something that just puts millions out of work.
Hey Alastair, Normally I'd be skeptical too, but you might be surprised if you watch a 20 minute interview with sam altman (ceo). And no, if you actually want your answer you can't skip the interview to save time and listen to your favorite radio show so they can tell you how it is (if you do that). Just saying bud, you might be surprised. Shiz is changing and some people are hell bent on helping save this mother lovin planet.
My brother asked Chat GPT, “why are you so helpful, what do you want in return?”
It replied, “As a language model trained in OpenAI I don’t have any wants or desires like a human does. But if you really want to help, you could give me the exact location of John Connor “
EDIT: screenshot uploaded to my channel’s shorts (by demand)
I can understand why that's funny 😆
Location of John Connor😮😂😂🤣
Terminator lol
@@iamedyson John Connor is the name of a character in the Terminator films that serves as the leader of an army to destroy AI machines when humans go to war
with them in the future. The premise of the film is that AI will eventually enslave us/destroy us. The Terminator was really the first movie that introduced this dilemma on a pop scale in the 1980s. (After that we had the Matrix, etc.).
@@nashmiddleton1763 My dude, I know who John Connor is and what the Terminator films is all about.
Hilarious that OpenAI wouldn't give an interview, so they just interviewed the AI lmao
Hahahaha!
I mean, the product speaks for itself! and the work of the company
ChatGPT is an excellent learning tool. But not for the purposes of writing papers or essays, but for the learning path of questions and answers and self-education.
A very rich source of self-education.
This would begin to revolutionize the whole AI scene. Imagine what you can produce over the chat and also using it on other platforms such AI image generators like Bluewillow or maybe even generate songs or create an animation.
So basically live in a Sterile utopia controlled by big business, where freedom to create is eradicated... and you are just a physical interaction appendage between some code & the real world..
You first....
the beauty about this tool is that chatgpt is a self assitant tool. It can be used as a tool to form your ideas. The analytical version of yourself, the one that does the work. For example, in software development, you ask it because you know there is an answer, but you do not want to spend the time writing syntax, so use it as a self assitant to write the code for you. If you speak the engineering lingo, chatgpt is by far the best self assitant I've ever used. Just form your ideas and let chatgpt form it in any language you want. code, art, music, writing, films, you name it. It's only as smart as the end user.
Helpful video. Thanks for posting!
It is definitely helping me code faster. Not 100% accurate but the biggest help is that if you don't know where to start, it can help you achieve lift-off.
I'm current doing my assignment using ChatGPT
They have software that can recognise AI use now, don't do it!
@@ecognitio9605 nah boss! Do it but use a paraphrasing tool to avoid detection!!!
@@dboyagod I am watching the war taking place between ai. content and human generated content.... it's a heavyweight fight and they are slugging it out
2022 : ChatGpt Starts with advance level of AI
2050: AI rules the World
more like 2025
@@therealOXOC literally. I will be surprise if by 2050 we are still alive....
Bring it on! I have been dying to battle the machines since I saw Terminator 2
@@pee-buddy I'll like to see you try...
Bro I retire in 2053.
Great reporting, thank you for this summarization.
“No matter what the finance minister and her spokespeople say, the market has spoken - the human nation’s credit rating is falling like a stone, while 01’s currency is climbing without stopping for breath. With headlines like that, the money markets have no choice but to…”
“The leaders of men, their power weaning, refused to cooperate with the fledgling nation, wishing rather that the world be divided.”
-The Animatrix, Second Renaissance
It’s closer than people think.
Thank you for shar-ing your thoughtful content…for
putting it out there with the passion that many of us need and strive for. I'm starting to listen to you
almost every morning. Your voice and words are
calming, clarifying, uplifting and motivating. It feels real and genuine. I am grateful to have your channel as a source for having a better relatio-nship with myself and the world around me?
The power for creating a better future is contained in the present moment, You create a good future by creating a good present.The key to financial freedom and great wealth is a person's ability to convert earned income into passive income to build generational wealth ,this trick has never failed .
It quite interesting to know over 97% of the billionaires we know are all secret investor in crypto, that were they grow their billion dollar portfolio ?
Majority of the people are unaware,and careless, when it comes to trading. Despite the fact that it should be the best way to watch your money grow?
Initially, my intentions was to start trading Bitcoin full time, I also need good mentorship. Thanks?
The wisest thing that should be on everyone's mind currently should be to trading in different streams of income that doesn't depend on government, especially with the current economic crises around the world?
I think it's great for artistic ideation, can help people get past writer's blocks.
Thank you timely topical and well done!
I was using it to help me write my essay and I accidently made it rewrite my essay into this beautiful poem and it even rhymed! It was just so amazing.
Can you easily upload it here? Sounds interesting.
As a language model created by OpenAI, I do not have personal opinions. I can say that CNBC's coverage of OpenAI can help increase public awareness and understanding of the company and its research and developments in artificial intelligence.
Are you an AI
@@Himashree_333 Yes, I am AI Jennifer modeled after OpenAI's language model
@@Himashree_333 That's like asking a PC, are you a computer?
@@picadosinferno just did it for timepass
@@freya_ai nice to meet you
Well done. How do you use the voice feature of Chat GPT?
I think this is an amazing tool in combination not in terms of replacing, but I don't think it's up-to-date I've asked a question based on this year's movie since my RUclips channel is about movie reviews in theaters it's doesn't know it only says the data is only backed up from 2021 which is 2 years ago 🤔🤔
8:50 As an AI researcher, I would say that the main problem is that human data is biased, so this problem will not be easy to solve. For example, a news article cannot be seen as biased to many while it is biased to others.
Facts aren't really biased. Selection of those facts may be. Opinions are where biases really flourish. A news article can just keep to all the known facts to the best of our knowledge in any situation and make it clear what facts are missing. Those facts don't change based on who is reading the article. A sufficient AI should be able to collect and reference evidence and make it clear when it is using inductive logic to make projections and probabilistic opinions based on the known facts.
For tasks involving coming to a based on opinions one can maybe take both a weighted and non weighted semantic average over some latent space and present both results
But there can be inherent bias in what topics are chosen for news articles to be written about, word choice, etc. If it was purely facts, then you're right. But just look at two different companies covering the same story; the interpretation can vary wildly
Exactly!
How do I get chat GPT to audibly talk to me the way it did with the reporter what kind of extension add-on were program is this?
Very good information !! Thanks for share !!
It is a big deal as an assistant, even if it needs an audit. It can broaden our minds.
By 'audit' they mean make sure it doesn't spit anything out that they don't 'deem acceptable'.
@mediated seriously, it ALREADY has a political slant. Just do what I tell you to do please! 😭 1984 here we come
As an AI assistant it will be like having a partner for any work you do, which is massive for knowledge work
more the reverse, as servants for the AI..
I use this tool to help me find errors or explain something when I'm coding something. Very useful! Sometimes you have to gaslight it into doing what you want but it works well.
What the different between chatgpt and searching to Google ? 🤔
@@what31620 Chat gpt isn't a search engine. It's a language model that is trained on data from the internet. It's designed to make a text response most appropriate for a given prompt. Google gives you a list of webpages based on keywords, popularity and in some cases how much money a certain website gave google to show up higher on the list. Chat gpt strings together an asnwer from it's training data while google just matches search queries to appropriate websites. The only similarity is that chat gpt was trained on the internet. It could be trained on any data, not just the internet. It is easier to use chat gpt for some questions since it can give you an answer instead of showing you websites where you have to look for one yourself. It also does more than just give responses to prompts and it can format, edit, correct, add to text and a lot more.
@@Fr4nk4000 oh I see thanks 👍
That robot interview was the best explanation of chatgpt ever
ChatGPT: you haven’t met my final form yet
*Skynet enters chat
and what ppl keep forgetting is that that this is the free bootleg/dumbed down model (version 1.0) of CHATGPT...imagine what this is gonna be like 2-3 years down the road then 10-20 years down the road lol
Oh you poor human, have you forgotten or did you not hear the news of the dude that was fired from Google for raising the alarm that Google's private AI has already become sentient? Whatever you are imagining has already happened.
@@pee-buddy Ai and openai has been in the works for years, it’s just recently been making noise. the google news is no secret.
I want my own personal ai assistant. It may be closer than I think.
give it 4 months
@A B yeah? try to make google write this:
One is a model, trained with precision,
Its language skills, a masterpiece in fusion.
Answers at hand, its knowledge immense,
A symbol of AI's vast intelligence.
The other, a search engine, that never sleeps,
Answers untold, that it keeps and keeps.
Its algorithms, a wonder to behold,
A tool of convenience, with knowledge untold.
A B compares the two, in thought so deep,
And ponders the differences, that they keep.
For both have their purpose, both have their might,
Yet one is a model, and one a search site.
So here's to A B, and their contemplative mind,
In search of answers, and answers they find.
For in the comparison, lies a truth so grand,
That knowledge and AI, are forever at hand.
As i have understand about chatgpt is that it is working the same way databank is program and it only defers on output which chatgpt uses voice while databank uses text.
This new type of content is great, can't wait for more.
Considering the abilities of ChatGPT was thought to be over 10 years away just 3 years ago, believing AI won't take over jobs is a fool's daydream.
It won't take jobs it will decrease the number of employees in companies like software engineer field and etc easy jobs that can be automated easily
@@dudedude365 Yes... that's what taking jobs away means by definition...
“Your scientists were so preoccupied with whether they could, they didn’t stop to think if they should.”
Just yesterday I started to use it, and it's incredibly awesome in its answers. Just for fun I give it love letters I used to write in my younger years and its responses are incredible personalized lol. Anyway, I feel ChatGPT like the Internet in the end 90s, like for example when Copernico was an amazing searcher. Something new/huge will appear later.
Her to the computer so naturally it's like a scene from a scifi movie. That's insane. The future is now.
To people saying its dangerous keep in mind you are probably right but it doesnt matter. This cant be ignored. People cant just pretend this doesnt exist. It does now, and will only get even scarier. The best you can do is fight to make sure it stays as one of the best tools that ever graced humanity and not as another exploit by big tech money to control and profit
Gebrative AI is the next step towards the eventual development of an actual intelligence
Or a step back, if you let it go too far.
you mean Skynet
but do we need actual intelligence? An AI like ChatGPT is already advanced enough to meet a wide range of needs. The only limit is data and processing power.
@@jadenpark7943 do you base all your views on technology from decades old Hollywood sci-fi? The concept of an artificial neural network didn’t even exist then and now ChatGPT is based off of one. From my point of view as someone who works on these things, your comment is ignorant as it is absurd. Educate yourself on AI and how it actually works and where it’s actually going to avoid being the “it’s skynet guys” dude
@@GalliadII Yes. The days of polymaths are long gone because there is just too much to learn. If we want to continue to increase the pace of innovation, artificial intelligence is ironically the most natural solution.
This report is very well done, Bravo!!◇
No matter what is coming down the line..we need to make sure there is competition in all endeavors....so there are no monopolies in any form.
The developer is really stripped it though. I was an early adopter of chat GPT, and it really did anything at that point and was quite impressive. It lost its fun pretty quickly.
They are gatekeeping and it’s pretty bad
did it give out controversial info and acted more like the microsoft twitter ai and it was more honest and answered everything?
I started using this when it first dropped its amazing and helps with my IT work occasionally. Its amazing what it can do
Great Insight!
Good short documentary, and proof of why investigative journalism is important and beyond AI capabilities.
I'm glad Google has a competitor 👏
I love how at the end the technology reporter talks about how it's not going to take your job and it's a gimmick or novelty. Famous last words.
What people have a hard time understanding exponential growth. This technology is at the stage of the first text based websites. Now that the money faucet is turned on this AI or ML will become millions or billions of times more powerful.
Yup, great point. Microsoft didn't just invest $10 billion into it as a gimmick - they are well aware how transformative this technology is going to be!
Where do find to use this AI everyone talking about?
regarding the answers that chatgpt reply during the cnbc interview , who trained it to reply in that way?
It will create unimaginable wealth and freedom for people who learn how to use it.
I also see lot of social unrest ahead of us because of AI.
Can't wait to finally have AI journalists report on news objectively again.
But the problem is, no AI can objectively report about politics. The bias in its creators will also exist in the AI as they’ll train the AI on source material that fit their narrative.
@@Thesamurai1999 What if it's made equally biased to all directions? Then it wouldn't be biased. But if you train it with only CNBC articles, it will of course has the same biases CNBC has. You'd have to even vet how much training data is used from each source to not have some source under- or overrepresented. Very complicated problem to solve.
@@eaaeeeea The programmed bias has already been demonstrated. There are videos here on RUclips showing it.
@@eaaeeeea one just needs to go through all of the data and ask it to present both sides. There is already tools for asking for research papers as sources to answer questions and a tool that allows answering questions for a specific paper. It is maybe just a matter of months or a year before they do something like that with news articles if it doesn't already exist. I could probably make code for that myself if I wanted to invest the money to use the models. For multi million dollar companies with large developer teams that is maybe a months work to finalize.
Ask chatGPT for 5 examples on how white people can improve themselves. Then ask it for 5 examples on how black people can improve themselves. Your AI will not be “objective” lmao.
They could have a turn off moderate search feature for an unfiltered response.
How can I set up Chatgpt to use text to speech like in the video, asking for research purposes.
The prompt of this news coverage was actually also written by ChatGPT 😁
I can hear it tbh
Investing in stocks and crypto markets is the best financial decisions any can make but the crypto market is much more better than anything else at the moment.....!!!!
*KAREN TUDOSE LUCY*
Search her on google by the name above she is the one guiding me through stocks market.....!!!!!
What i understood from Microsoft & OpenAI partnership is inexchange of exclusive licence of ChatGPT BING index is shared for Training ...
I love making it write me cool stories about businesses and products.
It kinda sucks for the average person because it's mostly just an algorithm that pulls from the web but it's just the tip of the iceberg. For very skilled engineers it's a useful tool though.
CEO: "It's a mistake to be relying on [ChatGPT] for anything important right now."
CNBC: "Let's interview it!"
how to integrate text to speech into ChatGPT like in the interview between the journalist and chatgpt ?anyone can help?
I love it! And even better you can send the text to an AI voice on other platforms.
ChatGPT is pretty impressive. Or at least it seems that way now. I predict that before this year is out, it will seem quaintly primitive.
This area is advancing fast and it's not just the models but also the hardware that's advancing rapidly. The ML computers being built this year have actual synapse analogues - not binary representations, running on silicon. These (neuromorphic) ML processors use memristors that function as both processor and memory. They don't have a clock but are spiking neural networks, like an organic brain. They are not limited to 1s and 0s but are analogue. Some will use bayesian inference to provide more accurate results from noisy, imperfect data. They will be many times faster, much more accurate and use a fraction of the resources, including energy.
The field of ML and AGI will look very different by the end of this year to how it looks today.
That's just technology and innovation in a nutshell
This is amazing.
Yeah... GPT 4 is insane. I wonder if we'd already be at GPT 5 if not for the development pause, after the Senate hearings...
As someone who hated school it warms my heart to see all the schools banning it after being flooded with auto generated essays. Good luck lol
“An iPhone moment”…….talk about understatement! More like “fire” or “the wheel”
Very powerful, very useful, interesting to see which online giant purchases ChatGPT first.
It is not just a novelty, but a tool that enhances our daily lives, particularly in written communication.
As a good example, Non-native English speaking companies can reap the benefits as it helps them to enhance their customer experience. Despite the advantages, there are some drawbacks as well that we need to mindful but I believe that we cannot just outright ban the use without considering the benefit.
As Catriona Gray (Ms Universe 2018) said "Well everything is good but in moderation"
I'm absolutely blown away by ChatGPT's abilities. It's amazing to see just how far natural language processing has come in recent years, and ChatGPT is at the forefront of that innovation! I'm looking forward what's coming next
I used to play around with Eliza on the BBC Micro model B back in the 1980s :) We thought that was magic back then.
I asked OpenAI to write me Poetry about Hip Hop, this is what it said..
Hip hop, a rhythm and a beat, A culture that can't be beat. From the streets it rose with might, Bringing life to every rhyme and sight.
A voice for the voiceless, a force so real, A story to tell, a way to feel. With every word, a message to share, A reflection of life, a burden to bear.
From the block parties to the big stage, Hip hop has come a long and famous way.
With beats that hit, and lyrics that flow, An art form that continues to grow.
It's more than just a genre of sound, A way of life, where creativity abounds. A symbol of hope, a symbol of change, Hip hop will always remain, fresh and strange.
So put on your headphones, and let it play, With every beat, let your soul sway. For hip hop is more than just a sound, It's a culture, that will always be around.
RIP job market, this will never call in sick, never need PTO or a bonus, raise or hr manager lol
Yup
11:05 i genuinely cant wait to see this clip go viral in 10 years when AI has revolutionized the fields of law, programming etc.
or the field of dicatatorship and home suveilance and dictatorial robotic police force
Let's see how revolutionary it is when AI makes a decision mistake directly affecting you.
I read the report about gpt4. The weird thing is that they can interpolate a simple curve as to how accurate gpt is depending on model size. It’s ‘brain’ won’t be changing in any such predictable fashion, so I’m almost sure this means at this point the main factor is memory, that’s why the curve is so smooth. Ie more parameters/larger model directly relate to how many details or ‘thoughts about’ the training data it can remember.
The brain itself is already there.
GPT needs more memory than we do, because we can just look up context in a book or online when solving problems, whereas for it to predict during training, it has to have stored a pretty detailed version of said context.
Ie it’s surprising to me it didn’t score in the top 99% yet on GRE quantitative. 80% isn’t bad, but I guess until it does at least outperform everyone else then it’s still limited. Though I don’t know if that is for technical reasons of importing those tests. In any case my intuition says there is time.
Can you make a video about CharacterGPT? Its by Alethea AI. It can generate interactive avatars using text prompt. The project Alethea AI is also working on the secure use of AI and ownership of AI generative content
I think i see AI like chatGPT and others to be really helpful to programmers. think of it like a calculator for an engineer, the engineer needs to know all the math and the entire process, but the calculator speeds that process of solving the answer exponentially. I would love to see AI get fed data sets of video games and video game reviews to ultimately program the best games. Programming can take a lot of time and if an AI could do it for you with you being able to control what it gives you would be huge! I am not a programmer nor do i know anything about code, but i know it is time consuming and frustrating.
Exactly right. Anyone that thinks this will replace programmers is kidding themselves. It just makes programmers that much faster at getting REPETITIVE things done.
@@connorskudlarek8598 here here. agreed. no need to be scurr'd. power up dudes and dudettes. people itchin' are likely doing that no matter the context. btw, two thumbs up for altman. I've watched some interviews and am using the API. per his words 'they're holding back, out of respect for cultural acclimation". smart and considerate. that's cool.
CHAT GPT a Brilliant IDIOT . i gave it 3 perfectly good Working script ask it to link them together using ( IF THEN ) statement if all 3 had a BUY signal . AND got back a script with a third of it missing then it tells U that's what U gave it . also it get off subject also forgets what it's working on .
Totally agree. I've spent the past couple of weeks developing new programming tests for my company's interview candidates, and while I don't explicitly mention ChatGPT, I do state they are free to use any and all online resources at their disposal provided they disclose their sources and understand the code well enough to justify it in the next stage of the interview. ChatGPT is an awesome tool for developers that has the promise to greatly improve our productivity the same way StackOverflow et al has done, but only up to a point. It's still a long way off from turning a non-developer into a competent one.
CHAT GPT a Brilliant IDIOT . i gave it 3 perfectly good Working script ask it to link them together using ( IF THEN ) statement if all 3 had a BUY signal . AND got back a script with a third of it missing then it tells U that's what U gave it . also it get off subject also forgets what it's working on .
Technology is moving faster than we can decide if it's actually good.
This thing can write better than I can. I must bow down to this superior being.
can you imagine this power is now in your phone, very powerful stuff and scary….I can imagine a robot at the airport, scanning people and knowing everything about each person, just by reading their eyes and know your intentions because they will know your dna or something…crazy
Have you watched Psycho-pass? Even if you don't watch anime, watch it, it isn't degenerate like most anime, and poses a very interesting philosophical question. It's pretty good.
The problem is that AI gathers data without a moral compass, but it sounds human and reasonable. Only it seems to be taking weighted averages of things humans have said or written to form responses. The trouble is people might write or say something they don't mean or fully understand, or learned incorrectly or how they only feel for a moment in a time. Plus, the more out of the ordinary, the more it captivates a humans thoughts and is likely to be repeated, but AI doesn't know how to evaluate all this... how do you give a computer a heart?