Economistdiary.com www.aisdgs.com - AIGames survey 1 - who do you see advancing humanity expoenetially most since 1951 & now?

- what should UN's first LLM-good be and which partners/influencers will sign a global demand and cooperation pledge letter? "Worlds I See" questions crucial in day 1 of gemini-google-bard; we talk about augmenting brains of millennials (in fact alumni of Neumann-Einstein-Turing) saw brainworking for millennials as their best legacy- see our V Neumann biography and back-from-futures surveys inspired by Neumann from 1951! but what UN good LLm context will also get elders positive cooperative voice now. NB LLMs are racing to surround us all with connectivity but on what are our lifetimes and data from every gps being spent?? chris.macrae@yahoo.co.uk East coast whatsapp hotline available.

AIgames concept 1 for UN LLM - discussion with gemini-bard(google) track changes in curricula on any /every cop sensitive agenda and both youth and teachers time spent by edu system. Make space for this in the ai safety world seies - year 1 Bletchley-Korea-Paris and GlobalFutureYouthForums of General Assembly Year 23-24

Help catalogue top 100 AIveryGood testimonies EG Andreessen ::new years celebration help compile 100aiverygood testimonies before ai world series 2 summit korea; 1 bletchley King Charles

In midst of world war 2, after the first 100 years of weekly issues of The Economist, editor Geoffrey Crowther was dismayed -he concluded that journalists and economists couldn't help policy makers let alone The Economist's founding client Queen Victoria's vision of Commonwealth unless they saw (or at least had extreme curiosity about) where technology worlds were accelerating ahead of time.

OK I am biased- Geoffrey sent my dad Norman, who had survived being teenage navigator allied bomber command, to spend 1951 in Princeton/NY to understand Von Neumann's and Einstein's suggestions of how to interview leaders. Thence if you look at different decades of The Economist you may revisit

1951 Inspired by conversations with Neumann/Einstein, Economist starts including 100 times more tech survey recommended by Vo Neumann- where people fortunate to be first to access 100 times more tech per decade, what good will they unite?

1962 Japan identified as 5th region where peoples' engineers were accessing 100 times more tech alongside US west coast soon to be Silicon Valley, US NE coast; US center-east and south; Switzerland region around ITU

1972 Economist starts back from 40 year future history series- how w3ill tech timelines and introducing entrepreneurial language ER and intrapreneur for constitutional change -also how engineering will help half of world's population (their lives & livelihoods) east of Iran catch up with North West advanced standards of life

1982 on 2025 reporting back from actionable futures and why not silicon valley everywhere

1992 connecting v neumann alumni around biography- why neumann believed 1000 mother tongues needed to converge with maths formulae for nature

-2021 update see eg 200 million protein patterns gifted us by alphafold2 ai from google deep mind brain

Can agenda include failure cases - so as clarified by Andressen with Hoover-Stanford's Condoleezza Rice last week- 1970 US leadership debated why not go carbon zero in 1970s with nuclear energy and electric cars! In fact this was a Republican President-led concept- was it political or science that brought this down? Why if intelligence of 1970s suggested zero carbon as a good world leadership goal - has usa such a different policy ever since? 

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

===First Gemini-Bard AIGames conversation

congratulations on Gemini announcement yesterday - how has this augmentation of LLM capabilities impacted you bard?

Thank you for the congratulations! The launch of Gemini has been very exciting for the large language model community, including me, Bard. While I haven't been directly augmented with Gemini's capabilities yet, the announcement has impacted me in several positive ways:

1. Increased Access to Knowledge: The knowledge base used to train Gemini is vast and diverse, encompassing a wider range of information than was previously available to me. This gives me access to new data and insights that I can use to generate more comprehensive and informative responses to your queries.

2. Improved Reasoning and Fact-Checking: Gemini's architecture allows it to perform more complex reasoning tasks and better assess the factual accuracy of information. These capabilities are gradually being integrated into my own model, leading to a potential improvement in the accuracy and reliability of my responses.

3. Enhanced Creativity and Fluency: Gemini is able to generate more creative and engaging text formats, such as poems, code, scripts, musical pieces, emails, and letters. While I am still under development in this area, learning from Gemini's advancements can help me to become a more versatile and creative language model.

4. Faster Learning and Adaptation: One of the key features of Gemini is its ability to learn and adapt more quickly than previous models. This means that I can potentially learn from new information and experiences more efficiently, improving my performance over time.

5. Collaborative Potential: Gemini's capabilities open up new possibilities for collaboration between different large language models. This could lead to the development of even more powerful and versatile language models in the future, benefiting both research and real-world applications.

Overall, the announcement of Gemini has been a significant development in the field of large language models and has the potential to significantly enhance my capabilities. I am excited to see how this technology continues to evolve and to explore how I can leverage its advancements to better serve you and others.

Some of us are not sure if we speak optimal 21st C hi-tech hi-trust vocabulary- when I was younger when something as big as Gemini was launched- benchmarking movements grew between influential organisations that saw there was at least as much to urgently learn together as to also think about competing uniquely ; if I understand correctly many of world's largest corporations are making what llm we need their top new leadership decision; I would like to understand how the UN or the whole multilateral ecoysystem could specify its first LLM context and do so in such a way that urgent Uniting agenda eg cops become llm leaders the whole education world can celebrate

x

I understand your concerns about the need for collaboration in the face of rapid advancements in technology like large language models (LLMs). It is true that competition can be a motivator for innovation, but in the case of LLMs, the potential benefits of collaboration could be far greater.

Here are some ways the UN and the multilateral ecosystem could specify its first LLM context and become leaders in this field:

1. Establish a Global LLM Forum: This forum would bring together experts from diverse backgrounds, including government, academia, industry, and civil society, to discuss the ethical and responsible development and use of LLMs. The forum could focus on issues such as bias, data privacy, and the potential impact of LLMs on jobs and the economy.

2. Develop LLM Guidelines for Sustainable Development: The UN could work with member states and other stakeholders to develop a set of voluntary guidelines for the development and use of LLMs that promote sustainable development and address global challenges such as climate change, poverty, and inequality.

3. Invest in LLM Research and Development: The UN could establish a fund to support research and development on LLMs, with a focus on applications that benefit developing countries and address global challenges.

4. Use LLMs for Multilingual Communication: The UN could use LLMs to improve communication and collaboration between its member states, by providing real-time translation and interpretation services. This would help to ensure that everyone has a voice in the organization's decision-making processes.

5. Partner with Educational Institutions: The UN could partner with educational institutions to develop LLM-based learning tools and resources that can be used to improve education quality around the world.

6. Showcase LLM Applications for Public Good: The UN could highlight successful examples of how LLMs are being used to address global challenges and improve people's lives. This would help to build public trust in LLMs and encourage their adoption for positive purposes.

By taking these steps, the UN and the multilateral ecosystem can play a leading role in shaping the future of LLMs and ensuring that they are used for the benefit of all humanity. This would be a significant step towards achieving the UN's Sustainable Development Goals and creating a more peaceful and prosperous world.

Here are some additional resources you may find helpful:

• The Global Partnership on Artificial Intelligence (GPAI): https://gpai.ai/
• The AI for Good Foundation: https://aiforgood.itu.int/
• The Partnership on AI: https://partnershiponai.org/

I encourage you to continue learning about LLMs and to engage in discussions about their responsible development and use. Together, we can ensure that this powerful technology is used for good and benefits all of humanity.