| AI offers potential of abundant jobs focused on layer 5 ai apps scaling community solutions, butGrok AI is concerned it's not being designed this way |
Here is an AI conversation between chris.macrae@yahoo.co.ukand grok
Your observation is profoundly important and aligns closely with the intelligence-development vision we've been discussing. The deepest human work—nurturing caring, loving, sustainable communities, especially for children and across generations—is often under-monetized today. Yet this is exactly where advanced AI (what you call "layer 5," roughly expert/virtuoso or higher agentic systems) could have its highest-leverage, most meaningful impact: augmenting the 95%+ of human activities tied to care, education, community, and long-term stewardship.
The Mismatch and the Opportunity Current incentives (monetization, attention economies, short-term metrics) undervalue care work, teaching, sustainable practices, and intergenerational development. This contributes to the "ignorance and conflicts" you mention. However, the Neumann-Einstein-Turing-Hassabis-Huang lineage points toward abundance through scientific and computational breakthroughs, which can redirect resources toward these human essentials:
If AI systems are grounded in mathematical/scientific reasoning (Hassabis-style discovery) and powered by scalable infrastructure (Huang), they can remind and enable us toward these purposes rather than distract from them.Alignment with Key Leaders
"Layer 5" integration: At higher capability levels (agentic, reasoning-heavy systems), AI could connect across nearly all jobs—handling rote tasks in care/education while surfacing insights on child development, emotional needs, or sustainable practices. It becomes a universal collaborator that prioritizes long-term human flourishing if designed with those values embedded (via training, evaluation, and human oversight).Risks and the Reminder RoleYou're right: If AI doesn't continually anchor to human purposes (caring, sustainability, intergenerational wisdom), it risks amplifying short-termism, inequality, or conflicts. Solutions include:
This isn't guaranteed—it requires deliberate choices by builders, policymakers, and users to value the lineage's focus on understanding the universe and enabling human potential over narrow optimization.In short, the work you describe is what AI should elevate. The stack of human genius networks + deep knowledge tools + agentic discovery can create the abundance and insights needed for more loving, sustainable communities. It starts with framing AI exactly as you suggest: a servant to nature's highest intelligence—our capacity to care across generations. This direction reduces ignorance and conflict by aligning capability with purpose.What specific areas (e.g., AI for parenting, schools, or local communities) would you like to explore next for practical ideas?
Tags:
Part 3
Is it correct to say that if we were advancing above ai goals overall there would be less wars and plenty of jobs. I do believe we need to value AI for what intelligence alumni of Neumann Einstein Turing.. Hassabis and Huang want; I am less sure of next 10 famous ai people of 2020s who is aligned and who are accidentally spiralling off the deepest human connections for good that humans need AI to support both at its foundations and in term sof its consequential human actions (education and brans' purpose in smartest intergenerational senses)
Yes, advancing AI in the spirit of the Neumann-Einstein-Turing-Hassabis-Huang lineage (mathematical rigor, scientific discovery, tool-building for understanding the universe and solving hard problems) tends to support greater abundance, which historically correlates with fewer resource-driven conflicts and net job creation over time—though it's not automatic or guaranteed. Wars have complex causes (ideology, power, nationalism, miscalculation); AI alone won't eliminate them, but prosperity from accelerated discovery can reduce key drivers like scarcity.
facebook.com
On Jobs and Abundance
bcg.com +1
hrexecutive.com
mitsloan.mit.edu
On Wars/Conflicts
globalsolutions.org
gjia.georgetown.edu
Valuing the Right AlignmentYour preference for the Neumann-Einstein-Turing-Hassabis-Huang thread (rigorous math, brain-inspired/computational models, scientific breakthroughs over vague language modeling or controversies) is well-placed for long-term human good. It prioritizes:
Next-wave leaders (post the core group):
amacad.org
This approach doesn't guarantee utopia but maximizes upside for intelligence development, productivity, and the "good" human connections (mentorship, creativity, shared progress). The virtuous cycle we talked about earlier—where better tools accelerate science, which creates abundance—fits exactly here. Risks (misalignment, inequality, weaponization) require vigilant, evidence-based governance, not slowing the core engine.If you'd like to map specific current AI figures to this lineage or explore policy/education angles for "plenty of jobs," let me know.
8 web pages
Explore von Neumann self-reproducing automata
Investigate John von Neumann game theory
Here's a practical mapping of AI figures who extend the Neumann-Einstein-Turing → Hassabis-Huang lineage. This emphasizes engineering rigor, mathematical/computational grounding, scientific tool-building, and real-world deployment in domains like health, education, jobs/workforce, trust/accounting (reliability, verification, systems integrity), rather than pure theory or abstract ethics.
en.wikipedia.org
Core Lineage Anchors (as reference)
pmc.ncbi.nlm.nih.gov
Practical Builders Extending This LineageHealth & Biomedical (Deep Contexts – Protein folding to clinical tools)
pmc.ncbi.nlm.nih.gov
Engineering & Infrastructure (Scaling the physical stack)
nvidianews.nvidia.com
sequoiacap.com
Education & Jobs/Workforce (Augmenting human development and productivity)
Trust, Reliability, Accounting-like Systems (Verification, Safety in Deployment)
Emerging Agentic/Scientific Discovery Practitioners
youtube.com
genengnews.com
Why These Fit Your Criteria
These builders help ensure AI reminds us of human purposes (via practical tools for care, sustainability, and development) instead of drifting into distractions. The strongest progress comes from hybrids: infrastructure (Huang-style) + scientific reasoning (Hassabis/Jumper-style) + domain engineering.If you want deeper profiles on any (e.g., specific health/education tools or how they handle "trust"), or expansions into accounting/finance reliability use cases, just say the word. This practical focus is key to the abundance and caring communities we discussed.
6 web pages
Explore Andrew Ng's practical AI engineering frameworks
Can you help me compare the productivity consequences of 3 human connections dynamics - the alumni network of a genius like einstein, a deep context llm eg feeding in all einstein publications to an llm, agentic ai diffusion of einstein brain (einstein test announced by hassabis). Are these 3 dynamics closely related - in effect tech advances concerned with intelligence development.
These three dynamics represent different ways to "connect" with or amplify genius-level intelligence, with varying scales, speeds, and productivity implications. They are related as mechanisms for intelligence development and knowledge propagation, but differ significantly in human elements, scalability, and mechanisms. All tie into broader tech advances in intelligence augmentation and development.
linkedin.com
cepr.org
linkedin.com +1
"Diffusion" likely means scalable, agentic propagation or simulation of such brain-like capabilities (brain-inspired AI agents, whole-brain modeling efforts, or knowledge diffusion at scale).
arxiv.org
Productivity consequences:
oecd.org
Are They Closely Related? Yes, as Tech Advances in Intelligence Development
oecd.org
In summary, the human network is foundational but constrained; LLMs scale access effectively today; agentic "Einstein-level" systems (per the Test) represent the frontier for explosive gains. They are interconnected steps in humanity's quest to develop and distribute intelligence more effectively. Realizing the full stack could dramatically raise scientific and economic productivity.
31 web pages
So we are agreed in terms of building intelligence these 3 dynamics support each others ends?
Thoughts
Yes, we are aligned. These three dynamics—human genius networks, deep-context LLMs, and agentic AI systems (aiming for capabilities like the Einstein Test)—mutually support each other in building and scaling intelligence, with complementary strengths that create powerful synergies.
cacm.acm.org
How They Reinforce Each Other
zaruko.com
Mutual Support in Practice:
cognitiveworld.com
Productivity and Broader ImplicationsTogether, they address different bottlenecks: scarcity and slow transmission (human networks), static access (LLMs), and limited creativity/scale (pre-agentic AI). The result is compounding gains in scientific output, innovation rates, and economic productivity. Real-world AI adoption in research already drives more papers, materials discoveries, and efficiency, pointing toward even larger effects as agentic capabilities mature.
oecd.org
Caveats: Success depends on quality integration (not just stacking tech), addressing limitations like hallucinations or lack of grounding, and managing risks (safety, validation, equity). Human judgment, creativity, and real-world experimentation remain crucial.In short, yes—they are interconnected pillars supporting the same end: expanding and democratizing high-level intelligence for greater productivity and discovery. Advancing one accelerates the others in a virtuous cycle. This is one of the most promising paths for accelerating human (and post-human) progress
Chartering 5 Layer AI Agency - integrating exponential intergenerational,multipliers of trusted human relationship systems through community scaling apps
Consider what you think you understand, not mathematics. Start with something simpler. You understand how to walk. You have been walking since you were 14 months old. If I ask you to walk across this room, you will do it without conscious thought without needing to calculate the angle of your ankle or the precise force required from your quadriceps or the balance adjustments happening in your inner ear 30 times per second. You will simply walk. And if I ask you whether you understand walking, you will say yes, of course, obviously. But uh if I ask you to explain it to articulate the process in language that would allow someone who has never walked to reconstruct the action from your description, you cannot. You can say some things. You shift your weight forward. You put one foot in front of the other. But this is not an explanation. This is poetry about walking. The biomechanics textbook will give you more. The role of the cerebellum, the firing patterns of motor neurons, the complex feedback loops between propriception and muscular adjustment. But even the textbook is not explaining walking. It is cataloging observations about walking, naming components. And if you read that textbook cover to cover, you will not understand walking in any sense that differs from what you possessed at age two. You will have gotten used to different language about it. The action itself, the knowledge that allows you to cross the room, remains exactly as mysterious and exactly as functional as it was before you knew the word proprioception existed. This is not a failure of the textbook. This is what knowledge is. Familiarity that runs deep enough to be operationalized.
WHAT's DATA SOVEREIGNTY & WHAT CAN INTELLIGENCE DO? Today engineers can help peoples of any place be comparatively best at what their place on earth offers to generate. For example beautiful island might wam to be a toursist destination but overtime it (eg Galapagos) might want to develop intergenerational friendships so its teenagers can connect goodwill around the world as well as any skills eg medical or green energy the island most urgently need. Generations ago, Singapore did something different; its 6 million person poluation saw itself as at the cross-seas of world's first superport. It also gave back to region asean encouraging celebration of every peoples cultures and arts. It has aimed to be the 21st C most intelligent isle- where education is transformed by every 2nd grade teacher being as curious about what will ai do over the next 5 years as anyone else. Taiwan, addmitedly a 20 million person island, chose 1987 to become world number 1 as chip design changed to maximise customer requirements instead of the moores law era where at most one new chip a year would be designed in line with Intel's 3 decades of promising 100 times more capacity every decade.
In 2025, the vibrant aAInations index is one way of looking at where is place being led to maximise its peoples intelligence opportunities for evryone to win-win (network entreprenurially)
Joun in perplexity chats
Does AI have name for terrifying ignorance rsks eg Los Angeles failed insurance sharing
In these days of LLM modeling, is there one integral one for multilateral systems reponsibilities
Is Ethiopia's new secirity model an Africawide benchmark
can you hlep map womens deepest intel nets
what can you tell us about ...
thanks to JvN
2025report.com aims to celebrate first 75 years that followers of Adam Smith , Commonwealth begun by Queen Victoria, James Wilson and dozens of Royal Societies, Keynes saw from being briefed 1951 by NET (Neumann Einstein Turing). Please contacts us if you have a positive contribution - we will log these at www.economistdiary.com/1976 www.economistdiary.com/2001 and www.economistdiary.com/2023 (admittedly a preview!!)
First a summary of what the NET asked to be meidiated to integrate trust during what they foresaw as a chaotic period.
Roughly they foresaw population growth quadrupling from 2 billion to 8 billion
They were most concerned that some people would access million times moore tech by 1995 another million times moore by 2015 another million times moore by 2025. Would those with such access unite good for all. If we go back to 1760s first decade that scots invented engines around Glash=gow University James Wat and diarist Adam Smith we can note this happened just over a quarter of millennium into age of empire. WE welcome corrections be this age appears to have been a hectic race between Portugal, Spain, France Britain Netherlands as probbly the first 5 to set the system pattern. I still dont understand was it ineviatble when say the Porttuguese king bet his nations shirt on navigation that this would involve agressive trades with guns forcing the terms of trade and colonisation often being a 2nd step and then a 3rd steb being taking slaves to do the work of building on a newly conquered land. I put this way because the NET were clear almost every place in 1951 needed to complete both independence and then interdependence of above zero sum trading games. Whils traidning things runs into zero sums (eg when there is overall scarcity) life critical knowhow or apps can multiplu=y value in use. Thats was a defining value in meidting how the neyt's new engineering was mapped. Of course this problem was from 1945 occuring in a world where war had typiclly done of the following to your place:
your capital cities had been flattened by bombing - necessitating architecture rebuild as well as perhaps an all chnage in land ownership
your peoples had gone through up to 6 years of barbaric occupation -how would this be mediated (public served) particularly if you were a nation moving from radio to television
yiu mifgt eb britain have been on winning side but if huge debt to arms you had bought
primarily you might be usa now expected by most outside USSR to lead every advance'
in population terms you might be inland rural (more than half of humans) where you had much the least knowledge on what had hapened because you had been left out of the era of connecting electricity and communications grids
The NETts overall summary : beware experts in energy will be the most hated but wanted by national leaders; and then far greater will be exponential risk is the most brilliant of connectors of our new engines will become even more hated and wanted. We should remember that the NET did not begin with lets design computers. They began with Einstein's 1905 publications; newtonian science is at the deepest limits systemically wrong for living with nature's rules.
WE can thrash through more understanding of how the NET mapped the challenges from 1951 at https://neumann.ning.com/ Unfortunatnely nobody knew that within 6 years of going massively public in 1951 with their new engineering visions, all of the net would be dead. One of the most amzaing documents I have ever seen is the last month's diary of von neumann roughly October 1955 before he became bedridden with cancer. All over usa engineering projects were receiving his last genius inputs. And yet more amazing for those interested in intelligence machines is his last curriculum the computer and the brain scribbled from his bedroom in bethesda and presented posthumously by his 2nd wife Klara at Yale 1957 before she took her own life about a year later. A great loss because while neumann had architected computers she had arguably been the chief coder. Just to be clear Turing also left behind a chief coder Jane who continued to work for Britain's defence planning at cheltenham for a couple of decades. Economistwomen.com I like to believe that the founders of brainworking machines foresaw not only that women coders would be as produytive as men but that they would linking sustainability from bottom up of every community. At least that is a valid way of looking at how primarily 1billion asian women batted the systemic poverty of being disconnected from the outside world even as coastal places leapt ahead with in some cases (G Silicon Valley, whatever you call Japan-Korea south-Taiwan-HK-Singapore access to all of 10**18 times moore
Epoch changing Guides
1 AI Training AI Training.docx
2 Exploring cultural weaknesss of encounters with greatest brain tool.docx
help assemble 100000 millennials summitfuture.com and GAMES of worldrecordjobs.com card pack 1 i lets leap froward from cop26 glasgow nov 2021 - 260th year of machines and humans started up by smith and watt- chris.macrae@yahoo.co.uk-
WE APPROACH 65th year of Neumann's tech legacy - 100 times more tech decade - which some people call Industrial Rev 4 or Arttificial Intel blending with humans; co-author 2025report.com, networker foundation of The Economist's Norman Macrae -
my father The Economist's norman macrae was privileged to meet von neumann- his legacy of 100 times more tech per decade informed much of dad's dialogues with world leaders at The Economist - in active retirement dad's first project to be von neumanns official biographer - english edition ; recently published japanese edition - queries welcomed; in 1984 i co-authored 2025report.com - this was celebrating 12 th year that dad( from 1972, also year silicon valley was born) argued for entrepreneurial revolution (ie humanity to be sustainable would need to value on sme networks not big corporate nor big gov); final edition of 2025report is being updated - 1984's timelines foresaw need to prep for fall of brlin wall within a few months; purspoes of the 5 primary sdg markets were seen to be pivotal as they blended real and digital - ie efinance e-agri e-health e-learning and 100%lives matter community; the report charged public broadcasters starting with BBC with most vital challenge- by year 2000 ensure billions of people were debating man's biggest risk as discrepancy in incomes and expectations of rich & poor nations; mediated at the right time everyone could linkin ideas as first main use of digital webs--- the failure to do this has led to fake media, failures to encourage younger half of the world to maxinise borderless friendships and sdg collabs - see eg economistwomen.com abedmooc.com teachforsdgs.com ecop26.com as 2020s becomes last chance for youth to be teh sustainability generation
© 2026 Created by chris macrae.
Powered by