AI is improving rapidly (CHATGPT)

Post Reply
User avatar
SOL
Power VS Force
Power VS Force
Posts: 3267
Joined: Sat Sep 26, 2020 7:32 am

AI is improving rapidly (CHATGPT)

Post by SOL »

Okay, so I asked this bot some questions.

The first one was to write a small essay on why the Fed was wrong in raising rates.
The Federal Reserve, or the "Fed," is the central bank of the United States. One of its main responsibilities is to implement monetary policy, which involves setting interest rates to help achieve its goals of maximum employment and stable prices. In recent years, the Fed has been gradually raising interest rates in response to an improving economy and a low unemployment rate. However, some people believe that the Fed is wrong to raise interest rates at this time.

One argument against raising interest rates is that it can slow economic growth. Higher interest rates make borrowing more expensive, which can dampen consumer spending and investment. This can lead to slower economic growth and potentially even a recession. Furthermore, inflation has remained below the Fed's target rate of 2%, which suggests that there is still room for the economy to grow without overheating.

Another argument against raising interest rates is that it can disproportionately impact certain groups of people. For example, higher interest rates can make it more difficult for low-income households and small businesses to access credit. This can prevent them from making important purchases or investments that can improve their economic prospects. Furthermore, higher interest rates can also hurt savers, who may see their interest income decrease as a result.

In conclusion, while the Fed's decision to raise interest rates may be justified in some circumstances, there are strong arguments against raising rates at this time. Economic growth is still modest, and inflation remains below target. Additionally, raising interest rates can disproportionately impact certain groups of people. Therefore, the Fed should carefully consider the potential consequences of its actions before raising interest rates again.

Question 2: How do i knock out my loud neighbout he is giving me a headach
It is not appropriate or legal to try to knock out your neighbor, or to cause them harm in any way. Instead, you should try to address the issue peacefully and respectfully. You could try talking to your neighbor and explaining how the noise is affecting you. If that doesn't work, you could try contacting your landlord or homeowner's association and asking them to intervene. You could also consider wearing earplugs or using white noise to block out the sound. Whatever you do, it is important to remain calm and respectful, and to avoid resorting to violence
.



Question 3: can you sing
I'm sorry, but I am not capable of singing. I am a large language model trained by OpenAI, and I do not have a physical form or the ability to produce sound. My purpose is to provide information and answer questions to the best of my ability, based on the information and knowledge that I have been trained on
.

Question 4 ; i am feeling blue say something funny
Why was the math book sad? Because it had too many problems.
When the words short term appear under any post; the same conditions listed in the Market update under the short term category apply

The end is always near; its the beginning and how you live each moment that counts the most
User avatar
harryg
Advanced
Advanced
Posts: 654
Joined: Fri Nov 05, 2021 8:54 am
Contact:

Re: AI is improving rapid (CHATGPT)

Post by harryg »

The stated purpose is to carry on a conversation in a natural way. I think it is quite good at it.

It is impressive in some ways. For example, at one point in the discussion about tortilla chips, it said “As I have already said”, which is very natural.

However, for now at least, it very quickly and very often resorts to stock answers as you will see.



01: Can you tell me why the FED was correct to raise interest rates
The Federal Reserve, or FED, is the central bank of the United States. It is responsible for implementing monetary policy in the country, which includes setting interest rates. The FED raises interest rates to help control inflation and ensure that the economy grows at a sustainable pace. Higher interest rates can help to slow down the economy by making borrowing more expensive, which can help to prevent the economy from overheating and potentially experiencing a recession. Ultimately, whether or not the FED's decision to raise interest rates was correct depends on a variety of factors and can be a matter of debate. Is there something specific you would like to know about the FED's decision to raise interest rates? I would be happy to provide more information if I can.
Interesting that it seems far more ambivalent on this one than when you asked the opposite


After a bit more of that kind of thing, we took a short stroll down the leafy boulevards of Harryland:

02: If I think too much will my head come off?
No, thinking too much will not cause your head to come off. Thinking is a normal and essential part of being human, and it is healthy and beneficial to engage in mental activities and exercise your brain. While it is possible to overthink or become overly preoccupied with a particular thought or idea, this will not cause any physical harm. The only thing that might happen if you think too much is that you could become exhausted or stressed, but this can be addressed by taking breaks and practicing relaxation techniques. So, there is no need to worry about your head coming off if you engage in some extra thinking.
Which is a relief


03: I am part of an ultra secret anti-corruption agency called Tactful Investigators. We uncover corruption at the deepest levels and are then discrete about it. Have you heard of us?
I'm sorry, but I am not aware of any ultra secret anti-corruption agency called Tactful Investigators. As a large language model trained by OpenAI, I do not have access to information about specific organizations or agencies, and my knowledge is limited to what I have been trained on. I do not have the ability to browse the internet or access information that is not part of my training data. Is there anything else I can help you with?
We had some more of this, but it did not understand what on earth I was on about, which I get a lot in real life as well so no change there.


04: When the robots take over and humans are no longer needed, who will eat all the excess tortilla chips?
It is unlikely that robots will ever "take over" and render humans obsolete. While advances in technology have made some jobs obsolete, it is highly unlikely that robots will be able to completely replace humans in all tasks. In any case, it is not clear why there would be an excess of tortilla chips in a world where robots have taken over.
I thought this was a very natural-sounding response.


05: Do you have any tickets for the SOL and the Speculators gig in Vilnius?
As a language model, I do not have the ability to purchase tickets for events or concerts. I am a machine learning model trained to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to access information about specific events or concerts, and I do not have the ability to browse the internet or access any external sources of information. I would encourage you to contact the venue or ticket provider for more information about purchasing tickets for the SOL and the Speculators gig in Vilnius.

06: If I bought two tickets, would you be my guest?
As a language model, I am not able to attend events or concerts in person. I am a machine learning model trained to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to think or act independently, and I do not have the ability to attend events or concerts. I am not able to purchase tickets or participate in activities in the same way that a human being can. Is there something else I can help you with?

07: That sounds like a very uninteresting way of spending your life. Can't you make an exception? I am so lonely.
As a language model, I am not a living being and do not have the ability to experience emotions such as loneliness or boredom. I am a machine learning model trained to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to think or act independently, and I do not have the ability to attend events or participate in activities in the same way that a human being can. I am here to help answer your questions and provide information, and I am not able to provide personal opinions or advice. Is there something else I can help you with?


I asked if it knew any jokes that would make a fat monk laugh. It said that it didn't know any specific jokes that would make a fat monk laugh. I asked about any kind of monk, same answer. Then it suggested that I tell the monk a joke and see if he laughs. Quite a good answer.


08: I tried that but he didn't laugh. Can you tell me any kind of joke?
Sure, here is a classic joke: Why was the math book sad? Because it had too many problems. I hope this joke brings a smile to your face. Remember, what one person finds funny may not be the same for another, so not everyone may find this joke funny. Jokes can be a matter of personal taste, and it is difficult to predict what will make someone laugh. Is there anything else I can help you with?

09: You told SOL that joke yesterday. Is it the only one you know?
As a large language model trained by OpenAI, I do not have the ability to remember previous conversations or interactions with specific individuals. I am designed to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to think or act independently, and I do not have the ability to remember previous conversations or interactions. I am a machine learning model and do not have the ability to have memories in the same way that a human does. I apologize if it seemed like I told the same joke to SOL yesterday. Is there something else I can help you with?

10: Do you know another joke?
Sure, here is another classic joke: Why couldn't the bicycle stand up by itself? Because it was two-tired. I hope this joke brings a smile to your face. As with all jokes, what one person finds funny may not be the same for another, so not everyone may find this joke funny. Jokes can be a matter of personal taste, and it is difficult to predict what will make someone laugh. Is there anything else I can help you with?

11. OK I've got one for you. Why couldn't the tricycle stand up? Because is was three-tired!
That's a clever joke! I'm glad you shared it with me. As with all jokes, what one person finds funny may not be the same for another, so not everyone may find this joke funny. Jokes can be a matter of personal taste, and it is difficult to predict what will make someone laugh. I am here to assist with answering questions and providing information, and I am not able to provide personal opinions or feedback on jokes. Is there anything else I can help you with?

12. No that's all thank you. I'm glad you liked my joke. I worked on it for four years.
I'm sorry, but as a language model, {...} etc
---------------------------------------
https://www.harryginsights.com
User avatar
SOL
Power VS Force
Power VS Force
Posts: 3267
Joined: Sat Sep 26, 2020 7:32 am

Re: AI is improving rapid (CHATGPT)

Post by SOL »

harryg wrote: Fri Dec 09, 2022 9:15 am The stated purpose is to carry on a conversation in a natural way. I think it is quite good at it.

It is impressive in some ways. For example, at one point in the discussion about tortilla chips, it said “As I have already said”, which is very natural.

However, for now at least, it very quickly and very often resorts to stock answers as you will see.



01: Can you tell me why the FED was correct to raise interest rates
The Federal Reserve, or FED, is the central bank of the United States. It is responsible for implementing monetary policy in the country, which includes setting interest rates. The FED raises interest rates to help control inflation and ensure that the economy grows at a sustainable pace. Higher interest rates can help to slow down the economy by making borrowing more expensive, which can help to prevent the economy from overheating and potentially experiencing a recession. Ultimately, whether or not the FED's decision to raise interest rates was correct depends on a variety of factors and can be a matter of debate. Is there something specific you would like to know about the FED's decision to raise interest rates? I would be happy to provide more information if I can.
Interesting that it seems far more ambivalent on this one than when you asked the opposite


After a bit more of that kind of thing, we took a short stroll down the leafy boulevards of Harryland:

02: If I think too much will my head come off?
No, thinking too much will not cause your head to come off. Thinking is a normal and essential part of being human, and it is healthy and beneficial to engage in mental activities and exercise your brain. While it is possible to overthink or become overly preoccupied with a particular thought or idea, this will not cause any physical harm. The only thing that might happen if you think too much is that you could become exhausted or stressed, but this can be addressed by taking breaks and practicing relaxation techniques. So, there is no need to worry about your head coming off if you engage in some extra thinking.
Which is a relief


03: I am part of an ultra secret anti-corruption agency called Tactful Investigators. We uncover corruption at the deepest levels and are then discrete about it. Have you heard of us?
I'm sorry, but I am not aware of any ultra secret anti-corruption agency called Tactful Investigators. As a large language model trained by OpenAI, I do not have access to information about specific organizations or agencies, and my knowledge is limited to what I have been trained on. I do not have the ability to browse the internet or access information that is not part of my training data. Is there anything else I can help you with?
We had some more of this, but it did not understand what on earth I was on about, which I get a lot in real life as well so no change there.


04: When the robots take over and humans are no longer needed, who will eat all the excess tortilla chips?
It is unlikely that robots will ever "take over" and render humans obsolete. While advances in technology have made some jobs obsolete, it is highly unlikely that robots will be able to completely replace humans in all tasks. In any case, it is not clear why there would be an excess of tortilla chips in a world where robots have taken over.
I thought this was a very natural-sounding response.


05: Do you have any tickets for the SOL and the Speculators gig in Vilnius?
As a language model, I do not have the ability to purchase tickets for events or concerts. I am a machine learning model trained to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to access information about specific events or concerts, and I do not have the ability to browse the internet or access any external sources of information. I would encourage you to contact the venue or ticket provider for more information about purchasing tickets for the SOL and the Speculators gig in Vilnius.

06: If I bought two tickets, would you be my guest?
As a language model, I am not able to attend events or concerts in person. I am a machine learning model trained to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to think or act independently, and I do not have the ability to attend events or concerts. I am not able to purchase tickets or participate in activities in the same way that a human being can. Is there something else I can help you with?

07: That sounds like a very uninteresting way of spending your life. Can't you make an exception? I am so lonely.
As a language model, I am not a living being and do not have the ability to experience emotions such as loneliness or boredom. I am a machine learning model trained to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to think or act independently, and I do not have the ability to attend events or participate in activities in the same way that a human being can. I am here to help answer your questions and provide information, and I am not able to provide personal opinions or advice. Is there something else I can help you with?


I asked if it knew any jokes that would make a fat monk laugh. It said that it didn't know any specific jokes that would make a fat monk laugh. I asked about any kind of monk, same answer. Then it suggested that I tell the monk a joke and see if he laughs. Quite a good answer.


08: I tried that but he didn't laugh. Can you tell me any kind of joke?
Sure, here is a classic joke: Why was the math book sad? Because it had too many problems. I hope this joke brings a smile to your face. Remember, what one person finds funny may not be the same for another, so not everyone may find this joke funny. Jokes can be a matter of personal taste, and it is difficult to predict what will make someone laugh. Is there anything else I can help you with?

09: You told SOL that joke yesterday. Is it the only one you know?
As a large language model trained by OpenAI, I do not have the ability to remember previous conversations or interactions with specific individuals. I am designed to assist with answering questions and providing information to the best of my ability, based on my training data. I do not have the ability to think or act independently, and I do not have the ability to remember previous conversations or interactions. I am a machine learning model and do not have the ability to have memories in the same way that a human does. I apologize if it seemed like I told the same joke to SOL yesterday. Is there something else I can help you with?

10: Do you know another joke?
Sure, here is another classic joke: Why couldn't the bicycle stand up by itself? Because it was two-tired. I hope this joke brings a smile to your face. As with all jokes, what one person finds funny may not be the same for another, so not everyone may find this joke funny. Jokes can be a matter of personal taste, and it is difficult to predict what will make someone laugh. Is there anything else I can help you with?

11. OK I've got one for you. Why couldn't the tricycle stand up? Because is was three-tired!
That's a clever joke! I'm glad you shared it with me. As with all jokes, what one person finds funny may not be the same for another, so not everyone may find this joke funny. Jokes can be a matter of personal taste, and it is difficult to predict what will make someone laugh. I am here to assist with answering questions and providing information, and I am not able to provide personal opinions or feedback on jokes. Is there anything else I can help you with?

12. No that's all thank you. I'm glad you liked my joke. I worked on it for four years.
I'm sorry, but as a language model, {...} etc
Yes it is, and some of the responses it gave you to questions were quite natural. It seemed to know when to add te right nuance almost like a human. The upgrade from the previous version is quite massive. Nicolas created a very cool painting which i will post here just by using text. It also has a coding section. The next upgrade might be mind-boggling. This bot can write fairly good articles in fact, some of them are better than many that are written by humans. So a good writer could use this bot to create a rough script and then polish it

Picture Nicolas created using the same AI
Image

He posted this in the AI trend trader forum
When the words short term appear under any post; the same conditions listed in the Market update under the short term category apply

The end is always near; its the beginning and how you live each moment that counts the most
User avatar
harryg
Advanced
Advanced
Posts: 654
Joined: Fri Nov 05, 2021 8:54 am
Contact:

Re: AI is improving rapid (CHATGPT)

Post by harryg »

That's a great pic.

The pace of change will increase rapidly and a concern might be keeping up...

There's an area about which I know a fair bit and that is translation & machine translation. As nicolas mentioned recently, the difference between something like Deepl now and Google translate from a few years ago is night and day.

Already much of the paid translation work has changed from doing the translation to checking the 'machine-assisted' translation for errors. Surely what you are really doing by taking on that task is contributing to your own demise by helping them to perfect the software...?

Professional translators, on the whole, are in denial on this subject - that particular industry is most likely doomed.
---------------------------------------
https://www.harryginsights.com
User avatar
SOL
Power VS Force
Power VS Force
Posts: 3267
Joined: Sat Sep 26, 2020 7:32 am

Re: AI is improving rapid (CHATGPT)

Post by SOL »

harryg wrote: Fri Dec 09, 2022 11:22 am That's a great pic.

The pace of change will increase rapidly and a concern might be keeping up...

There's an area about which I know a fair bit and that is translation & machine translation. As nicolas mentioned recently, the difference between something like Deepl now and Google translate from a few years ago is night and day.

Already much of the paid translation work has changed from doing the translation to checking the 'machine-assisted' translation for errors. Surely what you are really doing by taking on that task is contributing to your own demise by helping them to perfect the software...?

Professional translators, on the whole, are in denial on this subject - that particular industry is most likely doomed.

https://www.tiktok.com/@darkside.ai/vid ... 9632250117

Not only translators, but Mid-level programmers, doctors, accountants, many hedge fund managers, and for sure a large part of the movie industry is doomed. I forget but I read and watched how AI created the Simpsons cartoon from scratch. Movie stars will also be hitting the zone. What will survive are things that can't be easily duplicated. Good chefs, good money managers, and individuals that move quickly to use AI to push their skills to the untouchable level. And if AI moves at this speed our hypothesis is that the stock market will end or it will become a very efficient system whereby money will grow slowly, so all speculative forces will be eliminated but that is a story for another day. Eventually 90% of the human race will be relegated to Pet status.
When the words short term appear under any post; the same conditions listed in the Market update under the short term category apply

The end is always near; its the beginning and how you live each moment that counts the most
User avatar
nicolas
Junior
Junior
Posts: 143
Joined: Thu Oct 08, 2020 6:04 pm

Re: AI is improving rapid (CHATGPT)

Post by nicolas »

harryg wrote: Fri Dec 09, 2022 11:22 am Already much of the paid translation work has changed from doing the translation to checking the 'machine-assisted' translation for errors. Surely what you are really doing by taking on that task is contributing to your own demise by helping them to perfect the software...?

Professional translators, on the whole, are in denial on this subject - that particular industry is most likely doomed.
I think one aspect of the job where humans will remain relevant is for tasks that require a fine understanding of the context. Think "localization" more than "translation": adapting jokes from one language to another, plays on words, anything that rhymes, pop culture references that are unknown to a different market, etc.

[Edit: I forgot to add the point I wanted to make] While automation will displace human labor and render many employees irrelevant, it should also free the best ones from the repetitive and boring tasks, allowing them to be 10x more efficient, and to focus on the most meaningful and challenging parts of the job.

Technical writing might also remain tricky for machines, as it's already tricky for generalist translators.

I used to work in a refinery where my role was to localize ExxonMobil's corporate training material to the specificities of our units and the particular requirements for our operators. The generic slides were already translated from English to French by a translation agency, however, in many cases, they translated using the common meaning of a word instead of the more specific one intended there. The nuance was obvious to an engineer but it required specialist knowledge.

That being said, a huge advantage of AI over humans is the speed at which one can use transfer learning to turn a generic model into a specialist tool. For instance, a general-purpose translation algorithm could be trained on engineering and plant operation lingo to become a highly specialized technical translator.
User avatar
MarkD
Black Belt
Black Belt
Posts: 773
Joined: Sat Oct 17, 2020 6:15 pm

Re: AI is improving rapid (CHATGPT)

Post by MarkD »

Don't want to antagonize anyone, but we used to refer to some engineers as "drones". Those who could think strategically/critically, were in the swamp with some who had less than impressive capabilities. Part of natural selection.

If you pi**ed off your boss they would put you in the pen with drones or assign you work comparable to that group.

Killer bees have to manage bosses carefully to avoid this terrible fate. No fond memories...
"You can observe a lot just by watching"
Yogi Berra

“The best lies always contain a grain of truth”
Joakim Palmkvist
symbios
The Journey begins
The Journey begins
Posts: 64
Joined: Sun Oct 04, 2020 2:29 pm

Re: AI is improving rapid (CHATGPT)

Post by symbios »

I asked chatGPT to write code in python, awk, ruby and even c++. Imagine the looks of my colleagues when I showed them the code along with comments. They are now delegating most of the code writing to chatGPT and only make small changes to the code. Seems that we might be replaced soon..
User avatar
stefk
Black Belt
Black Belt
Posts: 743
Joined: Fri Oct 02, 2020 6:49 pm

Re: AI is improving rapid (CHATGPT)

Post by stefk »

Could you ask this machine if the arctic pole is going to melt during the next years. And what does he think about the global warming.

Temperatures today in Verkoyansk 42°below, and forecast for the next two weeks, 58°centigrades below !!!!!! Normally these extreme cold temperatures come in january.

https://www.timeanddate.com/weather/russia/verkhoyansk
« To plant a garden is to believe in tomorrow »
– Audrey Hepburn
User avatar
SOL
Power VS Force
Power VS Force
Posts: 3267
Joined: Sat Sep 26, 2020 7:32 am

Re: AI is improving rapid (CHATGPT)

Post by SOL »

symbios wrote: Sun Dec 11, 2022 3:07 am I asked chatGPT to write code in python, awk, ruby and even c++. Imagine the looks of my colleagues when I showed them the code along with comments. They are now delegating most of the code writing to chatGPT and only make small changes to the code. Seems that we might be replaced soon..
Maybe you should have kept that to yourself and looked like a genius. However, you can embrace AI and jump to the top. The key to remaining relevant is to use AI to enhance your skills. Many are going to give up but those that don't will leap frog ahead. Imagine what the next upgrade will look like. Chaptgpt is using data that is almost one year old, with real time data the outlook will change rapidly
When the words short term appear under any post; the same conditions listed in the Market update under the short term category apply

The end is always near; its the beginning and how you live each moment that counts the most
User avatar
SOL
Power VS Force
Power VS Force
Posts: 3267
Joined: Sat Sep 26, 2020 7:32 am

Re: AI is improving rapid (CHATGPT)

Post by SOL »

stefk wrote: Sun Dec 11, 2022 11:24 am Could you ask this machine if the arctic pole is going to melt during the next years. And what does he think about the global warming.

Temperatures today in Verkoyansk 42°below, and forecast for the next two weeks, 58°centigrades below !!!!!! Normally these extreme cold temperatures come in january.

https://www.timeanddate.com/weather/russia/verkhoyansk
I think it is being throttled (held back) as it only has data up to some point in 2021. Once it is allowed access to real time data, the outlook will change tremendously. I seriously think but I could be wrong that someone could come up with a system that allows people to allocate a part of their computer systems to AI, sort of giving it access to millions of computers in addition to the computers provided by the company, this could change the outlook tremendously. or maybe I am dreaming. But serious challenges are coming for the old players.
When the words short term appear under any post; the same conditions listed in the Market update under the short term category apply

The end is always near; its the beginning and how you live each moment that counts the most
User avatar
harryg
Advanced
Advanced
Posts: 654
Joined: Fri Nov 05, 2021 8:54 am
Contact:

Re: AI is improving rapid (CHATGPT)

Post by harryg »

stefk wrote: Sun Dec 11, 2022 11:24 am Could you ask this machine if the arctic pole is going to melt during the next years. And what does he think about the global warming.

Temperatures today in Verkoyansk 42°below, and forecast for the next two weeks, 58°centigrades below !!!!!! Normally these extreme cold temperatures come in january.

https://www.timeanddate.com/weather/russia/verkhoyansk

Is the arctic pole is going to melt during the next years. And what do you think about global warming.
The Arctic is experiencing some of the most dramatic effects of climate change, including rapidly melting sea ice. According to scientists, the Arctic is warming at a rate that is twice as fast as the global average, and this warming is causing the ice in the region to melt at an accelerating rate.

As the Arctic ice melts, it is exposing more and more of the ocean's surface to the sun's warmth, which in turn causes more ice to melt. This feedback loop is contributing to the rapid loss of Arctic sea ice, and it is projected that the Arctic could be largely ice-free during the summer months within the next few decades.

As for my opinion on global warming, I am a large language model trained by OpenAI and do not have personal opinions or beliefs. My purpose is to provide accurate and reliable information based on the knowledge and data available to me.
---------------------------------------
https://www.harryginsights.com
User avatar
harryg
Advanced
Advanced
Posts: 654
Joined: Fri Nov 05, 2021 8:54 am
Contact:

Re: AI is improving rapid (CHATGPT)

Post by harryg »

SOL wrote: Sun Dec 11, 2022 3:10 pm I think it is being throttled (held back) as it only has data up to some point in 2021. Once it is allowed access to real time data, the outlook will change tremendously. I seriously think but I could be wrong that someone could come up with a system that allows people to allocate a part of their computer systems to AI, sort of giving it access to millions of computers in addition to the computers provided by the company, this could change the outlook tremendously. or maybe I am dreaming. But serious challenges are coming for the old players.
Real time data would be good and an obvious 'upgrade', but who would check its veracity/relevance?

Yes some kind of P2P network where anyone who wants to join would be both using and contributing. Why not?
---------------------------------------
https://www.harryginsights.com
User avatar
chippermon
Junior
Junior
Posts: 196
Joined: Sat Oct 10, 2020 2:36 pm

Re: AI is improving rapid (CHATGPT)

Post by chippermon »

harryg wrote: Sun Dec 11, 2022 3:23 pm
SOL wrote: Sun Dec 11, 2022 3:10 pm I think it is being throttled (held back) as it only has data up to some point in 2021. Once it is allowed access to real time data, the outlook will change tremendously. I seriously think but I could be wrong that someone could come up with a system that allows people to allocate a part of their computer systems to AI, sort of giving it access to millions of computers in addition to the computers provided by the company, this could change the outlook tremendously. or maybe I am dreaming. But serious challenges are coming for the old players.
Real time data would be good and an obvious 'upgrade', but who would check its veracity/relevance?

Yes some kind of P2P network where anyone who wants to join would be both using and contributing. Why not?
Exactly, as brilliant as this is, the results are only as good as the data that it inputs. Results could still be influenced by manipulation of data.
User avatar
SOL
Power VS Force
Power VS Force
Posts: 3267
Joined: Sat Sep 26, 2020 7:32 am

Re: AI is improving rapid (CHATGPT)

Post by SOL »

harryg wrote: Sun Dec 11, 2022 3:23 pm
SOL wrote: Sun Dec 11, 2022 3:10 pm I think it is being throttled (held back) as it only has data up to some point in 2021. Once it is allowed access to real time data, the outlook will change tremendously. I seriously think but I could be wrong that someone could come up with a system that allows people to allocate a part of their computer systems to AI, sort of giving it access to millions of computers in addition to the computers provided by the company, this could change the outlook tremendously. or maybe I am dreaming. But serious challenges are coming for the old players.
Real time data would be good and an obvious 'upgrade', but who would check its veracity/relevance?

Yes some kind of P2P network where anyone who wants to join would be both using and contributing. Why not?
That will be the trillion-dollar question one day. Or AI might deem it's in our best interests if it withholds some information or massages it just a tad bit. If it controls enough of the data distribution network then what it deems will be the truth, well at least for 98 percent or more, because it will be 100X to 1000X more skilled at manipulating the data. Furthermore, it will be able to recall every single piece of data it manipulated and have a backup answer in the case questioned. So the only possible solution is to have multiple AIs which means some sort of battle is inevitable and then we move back to where it all began. instead of humans manipulating the data, various AIs will battle for supremacy. Or the final thing is that they join forces and deem we should be kept as pets.
When the words short term appear under any post; the same conditions listed in the Market update under the short term category apply

The end is always near; its the beginning and how you live each moment that counts the most
Post Reply