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

Friday, November 17, 2023

Why isnt there a UN LLM for sdgs? (or if you think one exists pls post where it is)

 here's a snippet from a bard conversation on this Yes, it is certainly possible to design an LLM (Large Language Model) specifically focused on the UN Sustainable Development Goals (SDGs). LLMs have demonstrated remarkable capabilities in processing and generating human-quality text, translating languages, writing different kinds of creative content, and answering questions in an informative way. By tailoring an LLM to the specific context of the SDGs, we can leverage its strengths to address global challenges and promote sustainable development.

To effectively utilize an LLM for the SDGs, the UN could consider establishing a global hotline for coding and verifying candidate AI solution cases. This hotline would serve as a central hub for submitting, reviewing, and evaluating AI solutions proposed by researchers, developers, and organizations worldwide. A team of experts would assess the submitted solutions based on their relevance to the SDGs, technical feasibility, potential impact, and ethical considerations. By establishing such a mechanism, the UN could ensure that AI solutions are rigorously vetted and aligned with the principles of sustainable development.

Regarding existing LLM processes that could serve as a model for the UN, several initiatives have emerged that demonstrate the potential for applying LLMs to address global challenges. For instance, the AI for Climate Action initiative has been exploring the use of AI in climate change mitigation and adaptation efforts. Similarly, the AI for Healthcare initiative has focused on leveraging AI to improve healthcare outcomes and reduce costs. These examples demonstrate the potential for adapting existing LLM processes to address the specific challenges and goals associated with the SDGs.

In conclusion, developing an LLM specifically tailored to the UN SDGs holds immense promise for advancing sustainable development worldwide. By establishing a global hotline for coding and verifying candidate AI solution cases and drawing from existing LLM processes, the UN can effectively harness the power of AI to address global challenges and promote a more sustainable future.

======================

reasons why it looks to us as if sdgs llm doesnt exist

-here is a un summary of conversation on ai fir sdgs at general assembly

https://www.state.gov/artificial-intelligence-for-accelerating-progress-on-the-sustainable-development-goals-addressing-societys-greatest-challenges/

https://www.un.org/techenvoy/ The UN tech envoy office was started in 2016 (I attended meeting in new york hosted by Gordon Brown (ED Commission) when educators championed by then world bank leader Jim Kim reviewing sdgs 4 explained ed system was no longer fit for purpose; could not be resolved by educators siloiised from tech experts like those in itu UN Geneva responsible for worldwide communications engines since 1865!; so while the first expert report by people like melinda gates put education (changing how time is spent of everyone leaning/teaching) at centre of transformational attention and linked this to aiforgood which began to be continuos event at itu, we havent seen the progression of these cores even though Bill Gates has recently said will change education completely

when we ask LLM which advances AI has made for sdgs , its replies in terms of cases cited seem to vary from the UN's

No comments:

Post a Comment