AI 2023. Meet ChatGPT. - page 110

New comment
 
A global study by three universities (Stanford and the national universities of Singapore and Hong Kong) has proven that AI can read people's minds by analysing brain activity.

Based on this data, the neural network generated images with 84% accuracy, down to texture and colours.

The researchers concluded that brain scans provide enough information for the machine to get an accurate picture of what a person is thinking.


//and now imagine if a chip in the brain gives the necessary waves and you already see a thing nobody needs and want to buy it, because in the city warehouses have brought too much and did not have time to sell out.
 
Реter Konow #:

I suggest you write this list, since you're so enthusiastic. And we will analyse together how much they are needed there.

I still don't understand the essence of the whole topic, which is spread over 100+ pages here. Aren't we looking for practical application of ChatGPT? In a year's time, there will be more advanced AIs.

And the list. Well, I've already given dozens of different ideas here - https://www.mql5.com/ru/forum/441019/page106#comment_46148976.

I can write a hundred of them, if you just ask for the direction of labour activity.

 
Реter Konow #:

***

...

Name the AI models doing the above job in health services.

...

There are many AI models that do work in the health services industry. Some of them include:

  1. IBM Watson Health - used to analyse medical data and support doctors' decision making.

  2. Google DeepMind - used to analyse medical images and predict diseases.

  3. Babylon Health - used to diagnose and treat diseases through telemedicine and consultation with doctors.

  4. Zebra Medical Vision - used for automatic recognition and analysis of medical images.

  5. Enlitic - used to automatically recognise and analyse medical images and patient data.

  6. Insilico Medicine - used to develop new drugs and treatments based on analysing genetic information and other medical data.

  7. Medtronic - used to automate procedures in medicine, such as surgical procedures.

These are just a few examples of AI models used in healthcare services. With the advent of new technologies and the development of algorithms, we can expect to see even more AI models designed to perform tasks in medicine.

With one caveat. AI can now be implemented even in rural areas, rather than all these expensive developments for select clinics. And then it won't be that someone will have to look for a clinic in another country because there is advanced treatment there. AI will bring the very top of all scientific advances to every city.

 
I watched a video where an American man was suffering from his neighbour's chickens spoiling his lawn.

Yankee pulled himself together, ordered some gadget on Aliexpress, installed a video camera and a hose. He trained a neural network to find chickens on the video, point the hose at them and turn on the water. The chickens were driven away by the water jet, as if it were an armament and defence station, and then the problem disappeared.

If a civilian can build something with a neural network, one can only imagine what directions private and public companies are working on (in open and closed mode).
 
Vitaliy Kuznetsov #:
A global study by three universities (Stanford and the national universities of Singapore and Hong Kong) has proven that AI can read people's minds by analysing brain activity.

Based on this data, the neural network generated images with 84% accuracy, down to texture and colours.

The researchers concluded that brain scans provide enough information for the machine to get an accurate picture of what a person is thinking.


//and now imagine if a chip in the brain will give the necessary waves and now you see no one needs a thing and want to buy it, because in the city in warehouses too much brought and did not have time to sell out.
If you can, give me a link to the study.
 
Vitaliy Kuznetsov #:

I still don't understand the point of the whole topic, which is 100+ pages long. Aren't we looking for a practical application of ChatGPT? In a year's time there will be AIs a lot more advanced.

Why are you confusing all AIs? ChatGPT is a language model. No more than that. Obviously you don't grasp the difference between different neural networks.

The LLM itself is just a talker. It can talk and follow some instructions, but it is not capable of solving complex problems. It is more correct to consider it an advanced information service. All other types of neural networks already existed.

Let's assume that other profile neural networks and applications will be attached to the talker. It will turn out to be a multiprogramme interface, the only advantage of which will be in convenience. It will speed up the work of some specialists, but fundamentally will not change anything.

The world is changed by revolutionary scientific discoveries, and the appearance of ChatGPT is not such.
 
The future lies in the multiprogramme speech interface, which will penetrate most areas of intellectual labour and facilitate the routine work of many specialists.

Paradoxically, it does not change anything qualitatively.

 
Реter Konow #:
If you can, provide a link to the study.

https://www.techcult.ru/science/12043-iskusstvennyj-intellekt-sposoben-chitat-mysli

Retag Konow #:
Why are you confusing all AI? ChatGPT is a language model. No more than that. Obviously you don't grasp the difference between different neural networks.

The LLM itself is just a talker. It can talk and follow some instructions, but it is not capable of solving complex tasks. It is more correct to consider it an advanced information service. All other types of neural networks already existed.

Let's assume that other profile neural networks and applications will be attached to the talker. It will turn out to be a multiprogramme interface, the only advantage of which will be in convenience. This will speed up the work of some specialists, but will not change anything fundamentally.

The world is changed by revolutionary scientific discoveries, and the appearance of ChatGPT is not such.

Apparently you don't read your own thread. GPT4 can analyse pictures. This is already text + image. It writes code, generates tables, presentations, translates video into text, makes a short extract. When connected to a webinar, it shows in chat what topics are covered, what questions were asked and whether they were answered. If there was no answer to any question, it shows with text that there is a question but no answer, i.e. it monitors the completeness and quality of the work done by the person. So audio/video-in-text is also added.

You can upload a book/audio/video and get a brief extract on it and answers to any questions on the specified source.

In idea, globally, it is a recycling of accumulated information. Information is no longer accumulated, but recycled on demand. Let's remember how the teacher said that in all her years of work she had never read a better essay (and it was ChatGPT). So much for analysing a piece of writing. And it's in every comp.

Anyway, stick to your opinion and watch the world change around you. However, a man's world, is his own, so without changing your view, you can't see beyond your opinion. The Indians didn't see ships off the coast either.

Without spiritualising AI and all the unscientific nonsense, I think progress is in sight. It has started so stormy, and they also promise a quantum leap by the end of the year, so to deny the tech storm is to miss opportunities. And the competitiveness of an entrepreneur who doesn't use AI will not be competitive.


P.S. I believe the argument on this issue between us has reached an impasse (or a certain outcome). I believe that the world will change because of AI (GPT4, MJ5 (but it is better if there will be domestic analogues)) and it has already started, you believe the opposite. My opinion will not change. Conclusion, I will not argue and prove anymore)

 

As soon as these neurons appeared, I suspected something. In fact, I think they're the future.

 
Vitaliy Kuznetsov #:

https://www.techcult.ru/science/12043-iskusstvennyj-intellekt-sposoben-chitat-mysli

...

Thanks for the link. "Techcult" is a reliable source of reliable information (as the name suggests) referring (without actual links) to another reliable source.
1...103104105106107108109110111112113114115116117...216
New comment