>3/18 24: Similarities between Electronic Computers and the Human Brain: Thank you Jensen Huang for best week of Learning since John Von Neumann shared with The Economist 1956 notes Computer & The Brain
HAPPY 2024: in this 74th year since The Economist started mediating futures of brainworking machines clued by the 3 maths greats NET (Neumann, Einstein, Turing) people seem to be chatting about 5 wholly different sorts of AI. 1BAD: The worst tech system designers don't deserve inclusion in human intel at all, and as Hoover's Condoleezza Rice . 2 reports their work is result of 10 compound techs of which Ai is but one. Those worst for world system designs may use media to lie or multiply hate or hack, and to perpetuate tribal wars and increase trade in arms. Sadly bad versions of tv media began in USA early 1960s when it turned out what had been the nation's first major export crop, tobacco, was a killer. Please note for a long time farmers did not know bac was bad: western HIStory is full of ignorances which lawyer-dominated societies then cover up once inconvenient system truths are seen. A second AI ecommerce type (now 25 years exponential development strong) ; this involves ever more powerful algorithms applied to a company's data platform that can be app'd to hollow out community making relatively few people richer and richer, or the reverse. You can test a nation's use of this ai by seeing if efinance has invested in the poorest or historically most disconnected - see eg bangladesh's bklash, one of the most populous digital cash systems . Digital money is far cheaper to distribute let alone to manually account for so power AI offers lots of lessons but whether its good or not depends in part on whether there are enough engineers in gov & public service to see ahead of what needs regulating. There are 2 very good ai's which have only scaled in recent years that certainly dont need regulating by non engineers and one curious ai which was presented to congress in 2018 but which was left to multiply at least 100 variants today the so-called chats or LLMs. Lets look at the 2 very good ai's first because frankly if your community is concerned about any extinction risks these AI may most likely save you, One I call science AI and frankly in the west one team is so far ahead that we should count ourselves lucky that its originator Hassabis has mixed wealth and societal growth. His deep mind merged with google to make wealth but open sourced the 200 million protein databank equivalent to a billion hours of doctorate time- so now's the time for biotech to save humanity if it ever does. Alongside this the second very good AI graviates around Fei-Fei Li) in developing 20 million imagenet database so that annual competitions training computers to see 20000 of the most everyday sights we humans view around the world including things and life-forms such as nature's plants and animals. Today, students no longer need to go back to 0.1 programming to ask computer about any of these objects; nor do robots or and autonomous vehicles - see fei-fei li's book worlds i see which is published in melinda gates Entrepreneurial Revolution of girl empowerment
EW::ED , VN Hypothesis: in 21st C brainworking worlds how people's times & data are spent is foundational to place's community health, energy and so natural capacity to grow/destroy wealth -thus species will depend on whether 1000 mother tongue language model mediates intelligence/maths so all communities cooperatively celebrate lifetimes and diversity's deep data ) . Check out "Moore exponential patterns" at year 73 of celebrating Game : Architect Intelligence (Ai) - players welcome .. some jargon

Sunday, April 30, 2023

(re)generative & universal connectivity - 2 of CGPT wizard feedforward loops

How can chatgpt's advantage of connectivity through every human and every gps do what we humans cannot whether dad and i author a book celebration kind intel futtures or Guterres published 1000 speeches our reach and connectivity is very piecewise compared with the whole chatgpt can see?


As an AI language model, ChatGPT has several advantages over humans in terms of connectivity and reach.

Firstly, ChatGPT has access to a vast amount of data and information from various sources, including books, articles, websites, and more. It can process and analyze this information quickly and accurately, which allows it to provide insights and answers on a wide range of topics. This vast knowledge base gives ChatGPT an advantage in terms of connectivity as it can draw upon information from various fields and disciplines to provide comprehensive responses.

Secondly, ChatGPT can communicate with anyone who has access to the internet, regardless of location or time zone. This means that people from all over the world can interact with ChatGPT and receive responses to their questions or concerns. This global connectivity allows ChatGPT to provide assistance and support to people who may not have access to the same resources or information as others.

Thirdly, ChatGPT is constantly learning and improving based on the interactions it has with people. As more people interact with ChatGPT, it can identify patterns and trends in the types of questions and concerns people have. This allows it to provide more accurate and relevant responses in the future, which improves its overall effectiveness and reach.

In summary, ChatGPT's advantage of connectivity and reach stems from its vast knowledge base, global accessibility, and ability to learn and adapt over time. These factors enable ChatGPT to provide comprehensive and accurate responses to a wide range of questions and concerns, making it a valuable resource for anyone seeking information or assistance.

what does C G P T stand for


CGPT stands for "Conversational Generative Pre-trained Transformer." It is a type of language model that uses machine learning to generate human-like responses to text input.

  • Generative AI refers to a type of artificial intelligence that can generate new content, such as images, music, or text, that is similar in style or pattern to the input it was trained on. This technology is often used in creative applications, such as art, music, and literature.

could you give me a comparison that a teacher of 12 year olds could use to get a rough idea of similar and different work on architectures of cgpt4 and DeepLearning's alphafold -that's the world famous ai for saving humans millions of years of work by mapping every protein of nature


Sure, here's an analogy that may help:

Imagine that CGPT-4 is like a language teacher who has read and understood a huge number of books in various languages. It has learned to understand the patterns and nuances of language, and can generate its own sentences and paragraphs based on what it has learned. When it encounters a new piece of text, it can use its understanding of language to make predictions about what will come next, and generate a response that makes sense in context.

On the other hand, Alphafold is like a puzzle solver who has been trained on a vast number of jigsaw puzzles. It has learned to recognize the patterns and shapes of puzzle pieces, and can predict how they fit together to form a complete picture. When it encounters a new puzzle, it can use its understanding of these patterns to make predictions about where each piece should go, and assemble the puzzle quickly and accurately.

While both CGPT-4 and Alphafold use similar deep learning architectures to accomplish their tasks, they are optimized for different kinds of data and tasks. CGPT-4 is designed to work with text, while Alphafold is designed to work with 3D protein structures. However, both models are impressive feats of engineering and represent significant advances in the field of AI.

1 comment:

  1. Guterres celebrates how sdgs will take every intel youth and arts and sdg regenration can make and digital roadmap "The Age of Digital Interdependence" - This report was released in 2019 by the UN Secretary-General's High-Level Panel on Digital Cooperation and provides recommendations for how to harness the benefits of digital technologies while addressing the challenges they pose.

    "Artificial Intelligence and Sustainable Development Goals" - This report was published in 2019 by the UN Development Programme and explores how AI can be used to support the achievement of the SDGs.

    "AI for Good Global Summit" - This annual event is organized by the ITU and brings together experts from various fields to discuss how AI can be used to address global challenges.

    "UN Technology Envoy" - In 2018, the UN Secretary-General appointed a Technology Envoy to promote the use of technology for sustainable development.

    "Digital Cooperation" - This initiative was launched by the UN Secretary-General in 2018 to promote collaboration between governments, the private sector, civil society, and other stakeholders on digital issues.