Deutsche Bank:::hewlett packard :: Softbank:: Samsung:: :siemens:: salesforce ::blackrock   BMW BNP:: foxconn :: dell::ford ....Coming To King Charles Language Modeling 100 Most Joyful Collabs inspired by Taiwan-Americans & Grace Hopper fans:  J1  Barbados amazon   Anthropic :: databricks
Silico -BIOtech: Genentech::CADENCE:: Hassabis::: CZI-Priscilla Chan ::; BioNeMo ..insurance
Who's Human Intelligence Who? 400 : 300 : 200 : 100 YL 2025 celebrates report that stanford and deep mind's human ai valley = United Humans benchmark of worldwide edu livelihood syytems of sdg generation2021 (celebrate 20 years on from 2001 wake upcall to silicon valley when 2001 abed and steves jobs' dream of womens world coop uni zooms womens hi-trust hi-goodness intel everywhere so that all people become lifelong students and mentors2022 worlds deepest health servant leaders reunited real communities simultaneously so what's 2023=24 to linkin first
.welcome - pls click here if you want to start at top of blog of AI and UN goals superstars

Sunday, December 31, 2023

A!20s.com 2023 year of AI Chat - we asked google bard/gemini to help debate what ai year of 2024 will celebrate

Dear Bard Could you help me shape my opinion og AI 2023 -

my fav short aiverygood youtube- King Charles, who's set bar high for the AI world series of 23-4 from Bletchley to Korea to Paris after Olympics to NY Sept 2024 UNsummitfuture.com

But overall in 2023, what I feel or see is: 

unlike imagenet and deep mind I simply find it hard to see who in Natural Language Processing did what big first moves on LLM & superchat -- people keep on referring to attention is all you need paper so I think its also good to see kaiser 2017 presentation at pi-school but I guess the problem is while imagenet is one clear databank,, and something like the game of go is mathematically evident as a pattern game - what goes into LLMs apart from some selection of anything that has even been on the web isnt that easy for 99.99% of humans to explain (or differentiate between models)

Advanced New Year's Alert from Bard Chat  absolutely right, pinpointing individual contributions in LLMs can be difficult compared to areas like image recognition or Go. Here's why: Complexity and Collaboration: Unlike Imagenet (data) or Go (pattern recognition), LLMs are complex machines with intricate architectures and training processes. Contributions come from diverse areas like neural network design, training algorithms, data selection, and even hardware optimization. Attributing specific breakthroughs to individuals within this collaborative environment can be challenging. Remember, LLM development is a complex and collaborative field. While identifying individual "first moves" might be challenging, appreciating the collective effort and understanding the contributions of various researchers, teams, and advancements can give you a deeper appreciation for the remarkable progress in this field. If you have specific interests within LLMs, feel free to ask! I'd be happy to help you navigate this fascinating and ever-evolving landscape.

Saturday, December 30, 2023

5 4 3 2 1

 AIVerygood.com with King's English networkers and WorldClassLMM:

.... aims to complete a 2024 new year mission (as leo burnett used to say: reach fir the stars you may not get there but you wont end up with a handful of muck either

TO FREE LEARNING FIRST CATALOGUE - first 1000 very good intelligences every student or teacher improving each others intelligences and peronal larning agench should be aware of and where relevant openly app in twin sister city communities

our 400 series links to those collaborators of moon shots on earth inspired by Jensen Huang is celebrating with very god use of milion times more acceerated computing architecure designed round machines that deep learn

300 series connects with king charles and commonwealth ai series as well as through 100+ Royal Societies- informally Queen Victoria appointed Diaspora Scot James Wilso to edit St James Royal Society chatsheets 1843 aka The Economist

200 Series are gamesters - ef inspired by Demin Hassabis- what computer training is needed to map nature's worl the way Einstein advocated from 1905 e=mcsquared  - from 1951 Economist editor Geoffrey Crowther asked dad to be twin cooresponent of being Trained by NET (Neumann Einsein Turing) as well as training Economists an Journalists in surveys like what good will people unite wherever they get first accees to at least 100 times more tech valu multipiers : such as Valley with Moores Law from 1965; the visions of those who experienced Tokyo's 1964 Olympics both first worldwide satllite broadcast and the year a Japanese calculator manufacturer ordered so many chips from Intel that it had to invent programmable chips not to be tied to much to one client; of course telecoms standars have since 1965! been cooperatively advanced out of Switzerlans ITU (even american scot graham alexander bell's phone hade to standar design with ITU) which was at affilated at League of Nations1920s when Einstein biurthed what afrer ww2 gor rebranded as UNESCO while the ITU remained twinned with Geneva's branch of UN also epicentre of Goal 3 WHO, UNCTAD win-win world trading games (Neumann) as well as eg nuckear peace wisdom?


100 Serues like Hassabis


Li spent her 2000s as a 20 something phd candidate bridging what neuroscience and cyber had not deeply linked in since the NET had all parted earth 1957; Standord 2009 was the first place in her then 30 years of life who valued her as more than weird- firunately hassabis was in the valley sponsored by london's royal society of neuroscince Gatsby; the idea that she would start an annual world championship around 20 million images (biggest databank machines ever tyrained on) matched coursera coders interest andrew ng, coursera biotect whiz daphne kolley; year 6 of the Yang family sponsoring stanford-yahoo professors of 100 times moore and interdicipliary tech lab's first building on camus - so if not the eagleAI WHY (Womens Humans Youth) had landed; from 2012 the whole world began to chat - can human and machine brains augment each others ways of spending human lifetimes and society's data series


An interpersonnal Odyysey- back in 1983 i started 12 years elapsed time hired by Unilever to do the data on empathy with muslim women market needs- fortunately we spoent 12 yesrs on marketing beauty is a womens self-confidence - see case study in my book Branch Chartering 1995 - with Economist Intelligence Unit - in search of organisations and networks with unique purposes- who would uniquely miss what if you inage and realty of your id did not exist. This matches challenges of TRillion Dollar Audirs first debated Brokookings Unseen Weath 2000 and EU rism Intangibles Crisis Union 2001 and at Fazle Abed's 65 birthday party hosted by Steve Jobs family across Valley 2001 - whence series 500 intelligences are female storytellers who took over parts of my old grey cells (thank googness). When I say my i include my family trr- dad as teen navigator allied bomber command burma; maternal grandad as quaret of century chief justice mediatir with Gandhi mumbai; var=ious scots missionaries who have a very peculiar way shared with Glasgow University of reasing Smith's last book on markets and nature before artificial engineers emerged round James Watt, and first book on transprency of geoploitics 16 years into life with engines

999 Mes Nurjahan Begum - mother of microcredit

998 Sunita Gandhi- 90 days can end illiteracy at any age from 5 up - her present in 60th year that her parents had run the world's largest schoool out of lucknow City Montessori also credited by Unesco as only one with 5th grade up peace curriculum

901 how do women & girls report the unique purpose of chips from my secod favorite island Taiwan (ok my ancestrs come from Arran not much more than 1000 vrains so luckily a space where starwars games have until millennilals century be no more than sci-fi sci fi