rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 7th, 2023 at 5:23:47 PM permalink
Even though this is not a gambling topic, I feel like after seeing this demo, it's going to have an impact on the industry. If I hadn't seen what previous models of Ai had already done, I'd believe this whole thing was a hoax. I don't think it is though.

There's no secret. Just know what you're talking about before you open your mouth.
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 7th, 2023 at 5:30:41 PM permalink
One question for all. Can you see any real difference in what this program is doing vs Hal 9000 in the Movie 2001, A Space Odyssey?
There's no secret. Just know what you're talking about before you open your mouth.
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
December 7th, 2023 at 5:40:54 PM permalink
Quote: rxwine

Even though this is not a gambling topic, I feel like after seeing this demo, it's going to have an impact on the industry. If I hadn't seen what previous models of Ai had already done, I'd believe this whole thing was a hoax. I don't think it is though.


link to original post



The video is obviously heavily edited, who knows how it really went. I don't trust any of this AI stuff been way too many instances of fraud just to get money for their projects. They will get it right someday but they're getting it mostly wrong so far.
"It's not called gambling if the math is on your side."
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
December 7th, 2023 at 5:43:20 PM permalink
Quote: rxwine

One question for all. Can you see any real difference in what this program is doing vs Hal 9000 in the Movie 2001, A Space Odyssey?
link to original post



That movie was made what, in the late sixties? We were amazed at Hal, now looking at it is amazing how stupid it is. The thing is dumb as a rock, LOL
"It's not called gambling if the math is on your side."
Wizard
Administrator
Wizard
  • Threads: 1493
  • Posts: 26508
Joined: Oct 14, 2009
December 7th, 2023 at 7:01:09 PM permalink
I thought the Mandarin word for duck was "ga," as in Lady Gaga.
"For with much wisdom comes much sorrow." -- Ecclesiastes 1:18 (NIV)
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 7th, 2023 at 7:15:48 PM permalink
Quote: EvenBob

Quote: rxwine

One question for all. Can you see any real difference in what this program is doing vs Hal 9000 in the Movie 2001, A Space Odyssey?
link to original post



That movie was made what, in the late sixties? We were amazed at Hal, now looking at it is amazing how stupid it is. The thing is dumb as a rock, LOL
link to original post



Actually, the Hal depiction was quite prescient. Hal could give wrong answers with a high degree of confidence. Same problem with current Ai. I wouldn't be surprised if Gemini could also read lips. Let's just hope it isn't planning to kill us.
s
There's no secret. Just know what you're talking about before you open your mouth.
Wizard
Administrator
Wizard
  • Threads: 1493
  • Posts: 26508
Joined: Oct 14, 2009
Thanked by
RogerKint
December 7th, 2023 at 9:17:21 PM permalink
Am I the only one who is underwhelmed by AI?
"For with much wisdom comes much sorrow." -- Ecclesiastes 1:18 (NIV)
darkoz
darkoz
  • Threads: 297
  • Posts: 11453
Joined: Dec 22, 2009
December 7th, 2023 at 9:40:17 PM permalink
Quote: Wizard

Am I the only one who is underwhelmed by AI?
link to original post



Like most technologies there are various aspects.

I recently worked on a musical project. I needed to use ai fo separate voice from instrumentals. Impossible without AI the AI did an excellent job.

Voice cloning was less effectual.

There are so many aspects to AI but the more creative human input the better. If you expect to just make a request and get back what you envision fat chance
For Whom the bus tolls; The bus tolls for thee
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 8th, 2023 at 5:00:14 AM permalink
Quote: Wizard

Am I the only one who is underwhelmed by AI?
link to original post



Just proves how easily we get used to something. That's why there's no reason to hide alien beings from us. In 6 months, we'd be over it. Unless we're all on the menu, in "What did you eat today" thread.
There's no secret. Just know what you're talking about before you open your mouth.
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 8th, 2023 at 5:05:11 AM permalink
Though, I would like to be around to see the all-purpose robot. Mows the lawn, or any multitude of tasks. Now that would be nice.
There's no secret. Just know what you're talking about before you open your mouth.
DRich
DRich
  • Threads: 86
  • Posts: 11728
Joined: Jul 6, 2012
Thanked by
Rigondeaux
December 8th, 2023 at 5:10:10 AM permalink
Quote: rxwine

Though, I would like to be around to see the all-purpose robot. Mows the lawn, or any multitude of tasks. Now that would be nice.
link to original post



They have been around for a long time. We call them wives.
At my age, a "Life In Prison" sentence is not much of a deterrent.
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
Thanked by
gordonm888SOOPOORigondeaux
December 8th, 2023 at 5:25:11 AM permalink
Quote: DRich

Quote: rxwine

Though, I would like to be around to see the all-purpose robot. Mows the lawn, or any multitude of tasks. Now that would be nice.
link to original post



They have been around for a long time. We call them wives.
link to original post



I mean, without the buggy software.
There's no secret. Just know what you're talking about before you open your mouth.
unJon
unJon
  • Threads: 14
  • Posts: 4606
Joined: Jul 1, 2018
December 8th, 2023 at 6:00:58 AM permalink
Quote: rxwine

Though, I would like to be around to see the all-purpose robot. Mows the lawn, or any multitude of tasks. Now that would be nice.
link to original post



Not sure how to embed a tweet but this boxing robot is cool.

https://x.com/shawnemerriman/status/1732875133940093384?s=46&t=u1mhgiArigQF9X45a7sWkg
The race is not always to the swift, nor the battle to the strong; but that is the way to bet.
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
December 8th, 2023 at 7:45:11 AM permalink
Quote: Wizard

Am I the only one who is underwhelmed by AI?
link to original post



This podcast I listen to everyday, the guy signed up for half a dozen different AI platforms that were supposed to do this and supposed to do that. Some of them cost a lot of money per month. None of them worked, none of them did what they were supposed to do. He wasted a lot of time on it and finally just dumped them all. We're 10 years behind where they're claiming that we are, right now they're just trying to raise money so they're bragging about stuff that doesn't even exist yet.

Reminds me of the early days of the automobile business. At one time there were a couple hundred different car manufacturers and most of them didn't work worth a damn. The ones that did work and were cost-efficient stuck around. That's what's happening with AI.
"It's not called gambling if the math is on your side."
darkoz
darkoz
  • Threads: 297
  • Posts: 11453
Joined: Dec 22, 2009
December 8th, 2023 at 8:51:23 AM permalink
Quote: EvenBob

Quote: Wizard

Am I the only one who is underwhelmed by AI?
link to original post



This podcast I listen to everyday, the guy signed up for half a dozen different AI platforms that were supposed to do this and supposed to do that. Some of them cost a lot of money per month. None of them worked, none of them did what they were supposed to do. He wasted a lot of time on it and finally just dumped them all. We're 10 years behind where they're claiming that we are, right now they're just trying to raise money so they're bragging about stuff that doesn't even exist yet.

Reminds me of the early days of the automobile business. At one time there were a couple hundred different car manufacturers and most of them didn't work worth a damn. The ones that did work and were cost-efficient stuck around. That's what's happening with AI.
link to original post



I love irony!
For Whom the bus tolls; The bus tolls for thee
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
December 8th, 2023 at 9:29:32 AM permalink
Grok premiered today on Twitter and people aren't very happy. Apparently it lies a lot already, it makes stuff up. It doesn't necessarily lie about facts, but it lies a lot if you ask it questions like, have you read a certain book, are you familiar with a certain movie. It will say yes it's very familiar with it and then when you ask it more detailed questions it has no idea what to answer because it doesn't have any experience with it. If you keep asking it will eventually tell you that it never read the book. Apparently it wants to please you so it'll tell you whatever it thinks you want to hear. We're a long ways from AI taking over the world, I think people can relax.
"It's not called gambling if the math is on your side."
Mukke
Mukke
  • Threads: 9
  • Posts: 139
Joined: Mar 24, 2019
Thanked by
Mentalrxwine
December 8th, 2023 at 12:45:05 PM permalink
Quote: Wizard

Am I the only one who is underwhelmed by AI?
link to original post



From other responses here, clearly you're not the only one.

I, however, am super excited. Of course there will be a lot of nonsense and vaporware, but there are absolutely scenarios that are amazingly useful, seem like magic and works enough of the time that it's worth relying on.

I use ChatGPT multiple times per day. A few interactions I've had that really show the everyday strength of ChatGPT:

https://chat.openai.com/share/657bf019-5138-4ddb-bd20-bf7665425f86 (I forgot the term for vaporware. ChatGPT to the rescue)
https://chat.openai.com/share/70a994e8-2b95-4cd4-89b6-a91010400891 (I had to explain a concept to a colleague and this was easier than writing it up my self or looking for a good example on the web)
https://chat.openai.com/share/4ad22f87-ddce-4592-9042-befb7389c50e (I needed to enlist ChatGPT to understand a term used by someone else on this site)

These are just some reason interactions.

In addition to ChatGPT, I use Github CoPilot. This is honestly the perfect case of an unintrusive copilot. I don't notice it's there, except when it writes comments and entire blocks of code for me on the fly. I don't have to ASK it to help me (though I could do that too). It just knows what I'm doing and provides meaningful, correct and comprehensive shortcuts for me.

To be perfectly frank, I think anyone who is not impressed and overwhelmed by these improvements are simply failing to use what's right in front of you.
Dieter
Administrator
Dieter
  • Threads: 16
  • Posts: 5558
Joined: Jul 23, 2014
December 8th, 2023 at 1:53:42 PM permalink
Quote: Mukke


https://chat.openai.com/share/4ad22f87-ddce-4592-9042-befb7389c50e (I needed to enlist ChatGPT to understand a term used by someone else on this site)
link to original post


(snipped - I think I'm allowed)

PM's are open, although it gave a pretty good breakdown. Nothing I'd disagree with, but the AI can't accurately fill in absent details.
May the cards fall in your favor.
heatmap
heatmap
  • Threads: 260
  • Posts: 2246
Joined: Feb 12, 2018
Thanked by
AxelWolf
December 8th, 2023 at 2:23:22 PM permalink
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
Thanked by
AxelWolf
December 8th, 2023 at 2:42:21 PM permalink
I watched that video earlier. Gemini in its final form is not released to the public at large. But Google should have been more transparent.
There's no secret. Just know what you're talking about before you open your mouth.
Hunterhill
Hunterhill
  • Threads: 53
  • Posts: 2151
Joined: Aug 1, 2011
December 8th, 2023 at 4:19:42 PM permalink
Quote: EvenBob

Grok premiered today on Twitter and people aren't very happy. Apparently it lies a lot already, it makes stuff up. It doesn't necessarily lie about facts, but it lies a lot if you ask it questions like, have you read a certain book, are you familiar with a certain movie. It will say yes it's very familiar with it and then when you ask it more detailed questions it has no idea what to answer because it doesn't have any experience with it. If you keep asking it will eventually tell you that it never read the book. Apparently it wants to please you so it'll tell you whatever it thinks you want to hear. We're a long ways from AI taking over the world, I think people can relax.
link to original post


It sounds like Grok was supposed to be a politician
The mountain is tall but grass grows on top of the mountain.
IndyJeffrey
IndyJeffrey
  • Threads: 13
  • Posts: 441
Joined: Feb 10, 2013
December 9th, 2023 at 3:55:46 AM permalink
Quote: Wizard

Am I the only one who is underwhelmed by AI?
link to original post



ChatGPT 3.5's response:

"Feeling underwhelmed by AI is a sentiment that some individuals share, and it's entirely normal to have varying opinions and experiences with this technology. AI has made significant advancements in various fields, but it might not always meet everyone's expectations or match the futuristic portrayals seen in movies and media.

Some reasons why someone might feel underwhelmed by AI could include:

Expectations vs. Reality: Popular culture often depicts AI in an exaggerated or unrealistic manner, leading to inflated expectations. Real-world AI might not match these portrayals.

Limitations and Challenges: AI has limitations and can sometimes struggle with complex tasks or understanding nuances that humans find easy. This can lead to disappointment when AI fails to deliver as expected.

Ethical and Societal Concerns: Concerns about AI's ethical implications, biases, and potential job displacement might dampen enthusiasm for its capabilities.

User Experience: Interacting with AI interfaces or applications that are not user-friendly or don't meet user needs can result in underwhelming experiences.

Maturity of Technology: In some cases, AI might not have reached the level of advancement or maturity that individuals anticipate in specific areas.

However, it's important to note that AI continues to evolve and improve rapidly. It has made remarkable strides in various industries, including healthcare, finance, transportation, and more. As technology advances and becomes more refined, AI may continue to surpass current limitations, potentially changing perceptions and addressing some concerns.

If you're feeling underwhelmed by AI, it might be helpful to explore different AI applications or learn more about specific advancements in the field. Additionally, understanding the current capabilities and limitations of AI can provide a more realistic perspective on its potential."
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
December 9th, 2023 at 5:02:48 PM permalink
Quote: EvenBob

Quote: rxwine

Even though this is not a gambling topic, I feel like after seeing this demo, it's going to have an impact on the industry. If I hadn't seen what previous models of Ai had already done, I'd believe this whole thing was a hoax. I don't think it is though.


link to original post



The video is obviously heavily edited, who knows how it really went. I don't trust any of this AI stuff been way too many instances of fraud just to get money for their projects. They will get it right someday but they're getting it mostly wrong so far.
link to original post



And here you go.

"The Verge reports that Google introduced Gemini, its latest and most powerful AI suite, amidst high expectations and fanfare. However, the tech giant found itself in the center of a controversy when it confessed to editing a demonstration video of the AI system, which it admitted shortly after op-ed published by Bloomberg raised suspicions about the video’s authenticity."

It was a phony baloney edited together fabrication just like I said it probably was. AI is nowhere near where all these tech people say it is so they constantly have to do things like this to prop it up. They are in such a big hurry to get a piece of the marketplace that they will do anything to make it look like it's a success.

https://www.breitbart.com/economy/2023/12/09/caught-red-handed-google-admits-staging-gemini-ai-demo-video/

"The company’s demo video, featuring a spoken conversation with Gemini as it identified drawings in real-time, was edited and did not involve an actual spoken prompt."
"It's not called gambling if the math is on your side."
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 10th, 2023 at 3:28:09 PM permalink
How do Ai companies make sure none of their programmers have installed a secret "backdoor'?
There's no secret. Just know what you're talking about before you open your mouth.
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
Thanked by
RogerKint
December 10th, 2023 at 4:47:16 PM permalink
Quote: rxwine

How do Ai companies make sure none of their programmers have installed a secret "backdoor'?
link to original post



They are all in such a hurry to become AI billionaires they don't have time to worry about the little stuff.
Everybody has all these Pie in the Sky predictions for AI and I personally think it's going to be a yawner. I think it's going to be mostly a dud as far as the public is concerned. Yeah they might be able to make a realistic sex robot eventually but nobody will be able to afford it unless you're Bill Gates.
"It's not called gambling if the math is on your side."
DRich
DRich
  • Threads: 86
  • Posts: 11728
Joined: Jul 6, 2012
Thanked by
rxwine
December 10th, 2023 at 5:31:10 PM permalink
Quote: rxwine

How do Ai companies make sure none of their programmers have installed a secret "backdoor'?
link to original post



I have written millions of line of code for the medical field, casino gaming, and financial industries. I have never worked in a field where I believe people are successfully find backdoors in software. Most don't even look and others it is very cursory, I have zero doubt that I could have put nefarious stuff in the software and it wouldn't be found until some major event happens.

The casino business was the worst for reviewing actual source code. It got to the point they wouldn't even look at it until a problem arises.
At my age, a "Life In Prison" sentence is not much of a deterrent.
Mental
Mental
  • Threads: 13
  • Posts: 1296
Joined: Dec 10, 2018
Thanked by
rxwine
December 10th, 2023 at 5:42:00 PM permalink
I worked on project 24 years ago involving a early form of language AI called latent sematic indexing. This required extensive computer processing for training and could only support very narrow queries. If you have never tried to use mathematical methods to model human language, you probably have no idea how difficult the problem is.

I agree with Mukke that the progress in AI (particularly LLM) is just astounding. When I read about the MCTS AI methods that became Go champions, it was easy for me to understand why that approach worked. I wrote a MCTS that was a very good Blokus player and much better than me. These AI game players are just optimizing board positions. Understanding human speech seems vastly harder. I still haven't the faintest idea what is happening under the hood with the new LLM AI systems. Some extremely hard problems have been solved by these teams.

Sure, the current AI systems will lie and hallucinate. But they write very good paragraph structures that would provide good starting points for a subject matter expert to edit and verify.
This forum is more enjoyable after I learned how to use the 'Block this user' button.
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 11th, 2023 at 4:26:29 AM permalink
Quote: Mental

I worked on project 24 years ago involving a early form of language AI called latent sematic indexing. This required extensive computer processing for training and could only support very narrow queries. If you have never tried to use mathematical methods to model human language, you probably have no idea how difficult the problem is.

I agree with Mukke that the progress in AI (particularly LLM) is just astounding. When I read about the MCTS AI methods that became Go champions, it was easy for me to understand why that approach worked. I wrote a MCTS that was a very good Blokus player and much better than me. These AI game players are just optimizing board positions. Understanding human speech seems vastly harder. I still haven't the faintest idea what is happening under the hood with the new LLM AI systems. Some extremely hard problems have been solved by these teams.

Sure, the current AI systems will lie and hallucinate. But they write very good paragraph structures that would provide good starting points for a subject matter expert to edit and verify.
link to original post



Yes "starting points". If you're serious about using what you find, you need to review what you're getting from them. But they're great for drilling down quickly into a subject and compiling information from different sources.

Can I find information myself? Surely, but not nearly so fast, as these things can parse specific questions.

Quote:

:

- Crocs (CROX): The footwear company saw its revenue grow by 77% in the first three quarters of 2021, and its stock price increased by 130% since March 2022⁴.
- Ford (F): The automaker bounced back from the pandemic and resumed its dividend payments. It also invested heavily in electric vehicles, launching the Mustang Mach-E and the F-150 Lightning. Its stock price rose by 123% since March 2022⁵.
- Dick's Sporting Goods (DKS): The retailer benefited from the surge in outdoor and fitness activities, posting strong sales and earnings growth. It also raised its dividend and announced a $1.5 billion share buyback program. Its stock price soared by 156% since March 2022⁵.
- CONSOL Energy (CEIX): The coal producer recovered from the slump in energy demand and prices, reporting improved margins and cash flows. It also reduced its debt and increased its production capacity. Its stock price jumped by 215% since March 2022⁶.
- Ardmore Shipping (ASC): The tanker company capitalized on the rebound in oil demand and transportation, delivering higher revenues and profits. It also repurchased shares and reinstated its dividend. Its stock price climbed by 224% since March 2022⁶.
- Hudson Technologies (HDSN): The refrigerant services company improved its operational efficiency and profitability, benefiting from the increased demand for cooling and heating solutions. It also expanded its customer base and product offerings. Its stock price rocketed by 267% since March 2022⁶.
- Paycom (PAYC): The payroll and human resources software company grew its revenues by 38% and its earnings by 52% in the first three quarters of 2021, beating analysts' expectations. It also increased its market share and customer retention. Its stock price advanced by 106% since March 2022¹.
- PDD Holdings (PDD): The Chinese e-commerce giant increased its active buyers by 45% and its revenues by 79% in the first three quarters of 2021, despite the regulatory challenges in China. It also diversified its revenue streams and invested in new technologies. Its stock price surged by 112% since March 2022¹.
- IonQ (IONQ): The quantum computing company went public through a merger with a special purpose acquisition company (SPAC) in October 2021, raising $650 million in gross proceeds. It also announced partnerships with Google Cloud, Microsoft Azure, and Amazon Web Services. Its stock price spiked by 133% since March 2022¹.
- SentinelOne (S): The cybersecurity company debuted on the stock market in June 2021, raising $1.2 billion in its initial public offering (IPO). It also reported impressive revenue growth of 121% and customer growth of 75% in the first three quarters of 2021. Its stock price leaped by 140% since March 2022².

Source: Conversation with Bing, 12/11/2023
(1) 3 Healthcare Stocks That Have More Than Doubled in Value Since the Fed .... https://www.fool.com/investing/2023/11/09/3-healthcare-stocks-that-have-more-than-doubled/.
(2) 3 Stocks That Can Double Again in 2022 | The Motley Fool. https://www.fool.com/investing/2022/01/03/3-stocks-that-can-double-again-in-2022/.
(3) 3 Top-Ranked Stocks That Doubled in 2022 | Nasdaq. https://bing.com/search?q=stocks+that+have+more+than+doubled+since+2022.
(4) 3 Hypergrowth Stocks to Buy Heading Into 2024. https://www.msn.com/en-us/money/savingandinvesting/3-hypergrowth-stocks-to-buy-heading-into-2024/ar-AA1li2ZG.
(5) This Generative Artificial Intelligence (AI) Stock Has Doubled in 2023, and It Can Still Deliver Magnificent Growth. https://www.msn.com/en-us/money/topstocks/this-generative-artificial-intelligence-ai-stock-has-doubled-in-2023-and-it-can-still-deliver-magnificent-growth/ar-AA1l5bcG.
(6) This Growth Stock Is Up 117% Since 2018 -- Here's Why It Can Double Again. https://www.msn.com/en-us/money/topstocks/this-growth-stock-is-up-117-since-2018-heres-why-it-can-double-again/ar-AA1kXT6I.

There's no secret. Just know what you're talking about before you open your mouth.
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
December 15th, 2023 at 10:37:42 AM permalink
Bill Gates says that generative AI in his opinion, and he's an expert, he thinks it's reached it's limit for now, it has hit a brick wall. Generative AI describes any type of AI that can create new content. So in other words the piece of crap that we have now in AI that lies, is lazy, gets things wrong constantly, seems to be getting stupider rather than smarter, that's as good as it gets for now. I predicted this, I said when this whole thing started that we're 10 years away from anything monumental because it always works that way. They had television at the 1939 World's Fair but it took 10 years before it started showing up in people's houses. We had microwave ovens at least 10 to 15 years before they started showing up in homes. And it's going to be the same thing with AI. It's going to be 10 years before it starts doing anything monumental.
"It's not called gambling if the math is on your side."
Mukke
Mukke
  • Threads: 9
  • Posts: 139
Joined: Mar 24, 2019
December 15th, 2023 at 11:44:34 AM permalink
Quote: EvenBob

Bill Gates says that generative AI in his opinion, and he's an expert, he thinks it's reached it's limit for now, it has hit a brick wall. Generative AI describes any type of AI that can create new content. So in other words the piece of crap that we have now in AI that lies, is lazy, gets things wrong constantly, seems to be getting stupider rather than smarter, that's as good as it gets for now. I predicted this, I said when this whole thing started that we're 10 years away from anything monumental because it always works that way. They had television at the 1939 World's Fair but it took 10 years before it started showing up in people's houses. We had microwave ovens at least 10 to 15 years before they started showing up in homes. And it's going to be the same thing with AI. It's going to be 10 years before it starts doing anything monumental.
link to original post



And the internet is a fad that will surely be forgotten in a few years!

It boggles my mind to see so many people easily dismiss Generative AI with the same recycles arguments about hallucinations, lies and inaccuracy.

Google sometimes returns bad information. Wikipedia can have bad info. Your professor can have bad info.

That doesn't change the fact that with a bit of healthy skepticism, all of these can be helpful. Once again, I use ChatGPT daily, and it provides a huge productivity boost for me bother personally and professionaly. I use Github CoPilot and it provides a huge productivity boost for me.

People who claim these things are not useful today, and somehow predict they won't be useful in the near future, simply has no idea what they are talking about.

Do you have a hammer in your toolbox, or do you not see the value in hammers since they don't work very well with screws?
EvenBob
EvenBob
  • Threads: 441
  • Posts: 28697
Joined: Jul 18, 2010
December 15th, 2023 at 12:22:51 PM permalink
Quote: Mukke

I use ChatGPT daily, and it provides a huge productivity boost for me bother personally and professionaly. I use Github CoPilot and it provides a huge productivity boost for me.
link to original post



That makes you the exception, not the rule. I listen to a podcast everyday of a professional and he can't make AI work for anything that he does in the creative field. It's all hat and no cattle, makes giant claims and can't back them up yet.
"It's not called gambling if the math is on your side."
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
December 15th, 2023 at 4:35:26 PM permalink
Quote: EvenBob

Quote: Mukke

I use ChatGPT daily, and it provides a huge productivity boost for me bother personally and professionaly. I use Github CoPilot and it provides a huge productivity boost for me.
link to original post



That makes you the exception, not the rule. I listen to a podcast everyday of a professional and he can't make AI work for anything that he does in the creative field. It's all hat and no cattle, makes giant claims and can't back them up yet.
link to original post



No doubt you're referring to Professor Pouncey.
There's no secret. Just know what you're talking about before you open your mouth.
darkoz
darkoz
  • Threads: 297
  • Posts: 11453
Joined: Dec 22, 2009
December 15th, 2023 at 4:39:48 PM permalink
Quote: Mukke

Quote: EvenBob

Bill Gates says that generative AI in his opinion, and he's an expert, he thinks it's reached it's limit for now, it has hit a brick wall. Generative AI describes any type of AI that can create new content. So in other words the piece of crap that we have now in AI that lies, is lazy, gets things wrong constantly, seems to be getting stupider rather than smarter, that's as good as it gets for now. I predicted this, I said when this whole thing started that we're 10 years away from anything monumental because it always works that way. They had television at the 1939 World's Fair but it took 10 years before it started showing up in people's houses. We had microwave ovens at least 10 to 15 years before they started showing up in homes. And it's going to be the same thing with AI. It's going to be 10 years before it starts doing anything monumental.
link to original post



And the internet is a fad that will surely be forgotten in a few years!

It boggles my mind to see so many people easily dismiss Generative AI with the same recycles arguments about hallucinations, lies and inaccuracy.

Google sometimes returns bad information. Wikipedia can have bad info. Your professor can have bad info.

That doesn't change the fact that with a bit of healthy skepticism, all of these can be helpful. Once again, I use ChatGPT daily, and it provides a huge productivity boost for me bother personally and professionaly. I use Github CoPilot and it provides a huge productivity boost for me.

People who claim these things are not useful today, and somehow predict they won't be useful in the near future, simply has no idea what they are talking about.

Do you have a hammer in your toolbox, or do you not see the value in hammers since they don't work very well with screws?
link to original post



It's difficult to take seriously someone who believes AI is worthless after attempting to use it to prove roulette claims.

Just goes to show he wasn't really serious.

He can respond in that thread he has permission to speak.
For Whom the bus tolls; The bus tolls for thee
AxelWolf
AxelWolf
  • Threads: 164
  • Posts: 22282
Joined: Oct 10, 2012
December 15th, 2023 at 7:05:22 PM permalink
I have yet to experiment with any AI such as ChatGPT.

Is there a learning curve on how to use it for more complicated things such as writing codes or programs or whatever else someone might need it for?

From what I've seen so far, when it comes to the average person it seems like AI is just a more advanced search engine that can half-assed put stuff together for you.

But as I said, I've never used it so I don't really know.

Can someone who uses AI give us examples of exactly what they use it for and how it helps them get their work done faster and better?

Someone wake me up when I can tell the AI program what I want done(within reason) and it just does it for me using Google search by voice feature.
Example: Okay Mr. AI create a Gmail email account named AxelWolfinvegas or something similar if that's taken send the password information to my main email account then use that Gmail account that you created to send an email to Michael Shackelford at gmail.com asking him the following trivia question. What's faster than the speed of light? Monitor my email and let me know when and if he comes up with a response reply to his email letting him know if he got the answer correct or not along with the correct answer. Text me when you've completed this task. Text me and let me know if you encounter any problems completing this task.
♪♪Now you swear and kick and beg us That you're not a gamblin' man Then you find you're back in Vegas With a handle in your hand♪♪ Your black cards can make you money So you hide them when you're able In the land of casinos and money You must put them on the table♪♪ You go back Jack do it again roulette wheels turinin' 'round and 'round♪♪ You go back Jack do it again♪♪
darkoz
darkoz
  • Threads: 297
  • Posts: 11453
Joined: Dec 22, 2009
December 15th, 2023 at 8:56:23 PM permalink
Quote: AxelWolf

I have yet to experiment with any AI such as ChatGPT.

Is there a learning curve on how to use it for more complicated things such as writing codes or programs or whatever else someone might need it for?

From what I've seen so far, when it comes to the average person it seems like AI is just a more advanced search engine that can half-assed put stuff together for you.

But as I said, I've never used it so I don't really know.

Can someone who uses AI give us examples of exactly what they use it for and how it helps them get their work done faster and better?

Someone wake me up when I can tell the AI program what I want done(within reason) and it just does it for me using Google search by voice feature.
Example: Okay Mr. AI create a Gmail email account named AxelWolfinvegas or something similar if that's taken send the password information to my main email account then use that Gmail account that you created to send an email to Michael Shackelford at gmail.com asking him the following trivia question. What's faster than the speed of light? Monitor my email and let me know when and if he comes up with a response reply to his email letting him know if he got the answer correct or not along with the correct answer. Text me when you've completed this task. Text me and let me know if you encounter any problems completing this task.
link to original post



Axel, I have some experience with AI.

There are several variations and it really depends what use you want. What you suggested isn't possible now and I doubt it will ever be.

Basically it can be grouped into two main variants which I personally refer to as AI creative and AI non-creative.

AI non-creative is what everyone thinks of and is freaking everyone out. You go to say Midjourney and type in a sentence ex. "Create a realistic picture of Bill Gates in a dress sucking on a lolipop" and the AI gives you four (standard is four) variations of art. Sometimes it's amazing often it's not. And you can try different variations of words to see if you get different results.

So it's learning at the same time you are. You are learning what AI gives you based on your requests, what gets better results and over time (talking months) the AI learns what is expected from your requests.

A good example is asking AI for images with signs or logos or billboards. Half a year ago it would give you a sign with chicken scrawls. Now it correctly gives the word but usually misspelled (I asked for the word Show Boat and it created a poster with the word SShowBoaaatt" It's learning at a quick rate but it's still young.

At any rate the other form of AI is creative AI. This is the type that is awesome but requires a huge learning curve. Go to YouTube and search AI generated movies unreal engine for example and you will see some awesome home generated short films created in an AI called Unreal Engine (there are others like Unity). These are programs where AI allows users to learn code that they can generate fantastic films. The most amazing films are by people using unreal engine for over a year. It's a big learning curve. Just jumping in and you will spend a week to figure out how to generate just one image.

That is using AI to complement creative juices. You are using toggles to guide and create what you want to see (for example an animated person fighting would have to be animated the old fashioned way frame by frame. Instead you create key points and "skeleton joints" and AI creates the animation.

This "creative. AI is heavily used in Hollywood right now and is an invaluable tool for creating effects. Making Indiana Jomes young for the Nazi scenes in his latest film for example.

So this attempt to consolidate AI into one end all be all scenario is totally misguided.
For Whom the bus tolls; The bus tolls for thee
rxwine
rxwine
  • Threads: 212
  • Posts: 12220
Joined: Feb 28, 2010
January 22nd, 2024 at 12:31:55 PM permalink
I’m surely not a poet, but Ai can give plenty of help, which is a good purpose for creating anything.

The Sun is bright and bold,
The Moon is calm and cold,

The Sun is hot and fierce,
The Moon is soft and clear,

The Sun can burn your eyes
The Moon can mesmerize.

The Moon can't outshine the Sun,
It's just a poor reflection,

But when the day is done,
It's the Moon that gets affection.


Needs more work.
There's no secret. Just know what you're talking about before you open your mouth.
BTLWI
BTLWI
  • Threads: 6
  • Posts: 454
Joined: Nov 6, 2013
Thanked by
AxelWolfMukke
January 24th, 2024 at 4:35:33 PM permalink
Quote: AxelWolf

Can someone who uses AI give us examples of exactly what they use it for and how it helps them get their work done faster and better?



I uploaded an image screenshot of data to chatGPT. I ask ChatGPT to read the data within the image and create a graph for me.

AxelWolf
AxelWolf
  • Threads: 164
  • Posts: 22282
Joined: Oct 10, 2012
January 24th, 2024 at 6:08:48 PM permalink
Quote: BTLWI

Quote: AxelWolf

Can someone who uses AI give us examples of exactly what they use it for and how it helps them get their work done faster and better?



I uploaded an image screenshot of data to chatGPT. I ask ChatGPT to read the data within the image and create a graph for me.


link to original post

Assuming you can take random screenshots of data and it can do that, I can see how helpful this would be.
♪♪Now you swear and kick and beg us That you're not a gamblin' man Then you find you're back in Vegas With a handle in your hand♪♪ Your black cards can make you money So you hide them when you're able In the land of casinos and money You must put them on the table♪♪ You go back Jack do it again roulette wheels turinin' 'round and 'round♪♪ You go back Jack do it again♪♪
  • Jump to: