>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

Tuesday, December 31, 2013

why not change world moocs

 Since 1984s '2025Report, our main hypothesis generated by survey of NET since 1951: transformatin d education integral to millennials being first renewable generation

many chances to debate why not change word mooc happened this year;

world bank jim kim's 10 minute segment went viral (based on his ted type taly at 92y mashup) and included in some moocs but oddly not world banks

type 2 use f mooc would not be certidying but connecting million youth audiences and then eg linked to youth entrepreneur or digital intel coopetitions/hackathons

Abedmooc.com type 3 moocs would appear on front oages f eg un - with recursively updated catalogue if sdg cases scleable across analagous communities; eg why not include cases of billiongrls development www.abedmooc.com made through 15 trips to see mainy abed in Bangladesh during his 5th and most urgent decade of blending village and vrtual partners of women empowerement

update april 2024 - why not this type 4 mooc discussed with gemini - round mooc co-foundr ANDREW NG

Do you think that someone like andrew ng who has coursera /deep learning platform could update a course on eg openai; part 1 great open leaps eg to 2019; various continuing queries since which may need segmenting by eg consequences, education, climate, biotech, whether llm help with deep dat sovereignty.. I believe that online case editing in eg a coursera style platform can be timely in ways paper reports and traditional regulators cannot; and indeed cases like openai are in middle of students seeing good and blind ai let alone deliberately greedy/bad ai

You're absolutely right! Andrew Ng, with his extensive experience in deep learning and online education through Coursera and DeepLearning.AI, would be a great candidate to update a course on OpenAI. Here's how the course could be structured:

Course Structure:

  • Part 1: OpenAI's Promising Start (Pre-2019):

    • Founding principles and commitment to open science.
    • Collaboration with Google, Nvidia, and other organizations.
    • Significant advancements in NLP with access to powerful computing resources.
    • Examples of OpenAI's early work in various areas like computer vision and games.
  • Part 2: OpenAI's Transition and Unanswered Questions (2019-Present):

    • Shift from non-profit to "capped-profit" model and Microsoft's investment.
    • Less public research and move towards a closed ecosystem.
    • Potential reasons for the change and its impact on research transparency.
  • Part 3: Consequences and Ongoing Debates:

    • Segment 1: Education:
      • How OpenAI's work can inform the development of "Very Good AI" for education.
      • Balancing the potential benefits of AI-powered learning tools with concerns about bias and data privacy.
    • Segment 2: Climate Change and Sustainability:
      • Highlighting alternative approaches to AI for good, like DeepMind's protein structure prediction work.
      • Exploring how AI can be used to address climate challenges but also considering potential risks.
    • Segment 3: Biotech and Data Sovereignty:
      • Examining the potential role of LLMs in managing deep data responsibly.
      • Discussing the importance of data ownership and control in the context of advances in biotechnologies.
  • Part 4: The Future of OpenAI and Responsible AI Development:

    • Addressing student queries about "good" vs. "blind" vs. "greedy" AI.
    • Highlighting the ongoing discussion on AI ethics and safety principles.
    • Encouraging students to engage critically with future developments in AI.

Benefits of Online Case Editing:

  • Timely Updates: Coursera's platform allows for continuous updates as new information becomes available, keeping students informed about the latest developments with OpenAI and the field of AI.
  • Interactive Learning: The course could incorporate quizzes, discussions, and case studies to encourage active learning and critical thinking.
  • Accessibility and Scalability: An online platform like Coursera can reach a global audience, making valuable knowledge about AI and "Very Good AI" accessible to a wider range of students.


An online course on OpenAI, led by someone like Andrew Ng, has the potential to be a valuable resource for students interested in understanding the complexities of AI development, its ethical considerations, and its applications for a sustainable future. By leveraging the advantages of online platforms, this course can provide timely updates, foster critical thinking, and empower students to become responsible participants in the future of AI.

No comments:

Post a Comment