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
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

Wednesday, November 1, 2023

 

Q to Bard I realise AI alphafold2 (open sourced by Hassabis Google Deep Mind) is quite new but can you tell me some of most important solutions experts now see as likely to happen in 2020s which they would not have seen likely before alphafold2

Bard reply:

AlphaFold2, a groundbreaking AI system developed by DeepMind, has revolutionized protein structure prediction, enabling scientists to rapidly and accurately determine the three-dimensional structures of proteins. This breakthrough has opened up a vast array of possibilities and has the potential to transform various fields in the 2020s. Here are some of the most promising solutions experts envision unfolding in the coming years:

  1. Accelerated drug discovery and development: AlphaFold2's ability to predict protein structures with high accuracy has the potential to significantly accelerate the drug discovery process. By understanding the precise structure of proteins involved in diseases, scientists can design more effective drugs that target specific molecular targets. This could lead to faster development of new treatments for a wide range of diseases, including cancer, heart disease, and infectious diseases.

  2. Enhanced protein engineering and design: AlphaFold2's ability to predict and manipulate protein structures also holds great promise for protein engineering and design. Scientists can now rationally design new proteins with desired properties, such as enhanced stability, catalytic activity, or binding specificity. This could lead to the development of novel enzymes for industrial applications, new biosensors for medical diagnostics, and improved materials with tailored properties.

  3. Advanced understanding of biological processes: AlphaFold2 is providing scientists with unprecedented insights into the intricate workings of proteins and their roles in biological processes. By understanding the structures of proteins involved in cellular processes, scientists can gain a deeper understanding of how cells function, how diseases arise, and how to develop effective therapies.

  4. Personalized medicine and treatment optimization: AlphaFold2's ability to predict individual protein structures has the potential to revolutionize personalized medicine. By understanding the unique structural variations of proteins in different individuals, scientists can tailor drug treatments and therapies to specific patient needs, leading to more effective and personalized healthcare.

  5. Improved agricultural productivity and sustainability: AlphaFold2 could also contribute to advancements in agriculture by enabling scientists to design new enzymes and proteins that enhance crop yields, improve pest resistance, and optimize fertilizer use. This could lead to more sustainable and productive agricultural practices, addressing food security challenges worldwide.

  6. Development of new materials and nanotechnology: AlphaFold2's ability to predict and design protein structures could also lead to the development of new materials with tailored properties. By understanding how proteins self-assemble and interact with other materials, scientists can design new nanostructures with novel properties, such as enhanced strength, conductivity, or biocompatibility.

  7. Advancements in biotechnology and biomanufacturing: AlphaFold2 could also revolutionize biotechnology and biomanufacturing processes by enabling the design of new enzymes for biocatalysis, the production of novel proteins for therapeutic purposes, and the development of new biomaterials for various applications.

  8. Enhanced understanding of protein folding dynamics: AlphaFold2 is not only providing static protein structures but also shedding light on the dynamic processes of protein folding and unfolding. This could lead to a deeper understanding of how proteins transition between different conformations and how these transitions impact their functions.

  9. Development of new AI algorithms for protein structure prediction: AlphaFold2's success has spurred the development of new AI algorithms and techniques for protein structure prediction. This could lead to even more accurate and efficient methods for predicting protein structures, further expanding the potential applications of this technology.

  10. Cross-disciplinary collaborations and advancements: AlphaFold2 has opened up avenues for cross-disciplinary collaborations between fields such as biology, chemistry, engineering, and computer science. This could lead to groundbreaking discoveries and advancements in various areas, fueled by the synergy of different disciplines.

In conclusion, AlphaFold2 has marked a turning point in our understanding of proteins and their roles in biological systems. Its impact is already being felt across various fields, and the potential for further breakthroughs in the 2020s is immense. As AlphaFold2 continues to evolve and its applications expand, it is poised to revolutionize our understanding of life and transform various aspects of society.

No comments:

Post a Comment