DCAI--AI & Childhood Cancer ...AP July 2025 - INTELLIGENCE ENGINEERING'S ALPHABET : World Class Biobrains: Drew Endy, Matt Scullin, Daniel Swiger++- BI BioIntelligence, the most collaborative human challenge Mother Earth has ever staged?
NB any errors below are mine alone chris.macrae@yahoo.co.uk but mathematically we are in a time when order of magnitude ignorance can sink any nation however big. Pretrain to question everything as earth's data is reality's judge
Its time to stop blaming 2/3 of humans who are Asian for their consciously open minds and love of education. Do Atlantic people's old populations still trust and celebrate capability of generating healthy innovative brains? What's clear to anyove visting Washington DC or Brussels is a dismal mismatch exists between the gamechanging future opportunities listed below and how freedom of next generation learning has got muddled by how old male-dominated generations waste money on adevrtising and bossing. Consider the clarity of Stanford's Drew Endy's Strange Competition 1 2:
Up to “60% of the physical inputs to the global economy”7 could be made via biotechnology by mid-century, generating ~$30 trillion annually in mostly-new economic activity. 8 Emerging product categories include consumer biologics (e.g., bioluminescent petunias,9 purple tomatoes,10 and hangover probiotics11 ), military hard power (e.g., brewing energetics12 ), mycological manufacturing (e.g., mushroom ‘leather’ 13 ), and biotechnology for technology (e.g., DNA for archival data storage14 ). Accessing future product categories will depend on unlocking biology as a general purpose technology15 (e.g., growing computers16 ), deploying pervasive and embedded biotechnologies within, on, and around us (e.g. smart blood,17 skin vaccines,18 and surveillance mucus19 ), and life-beyond lineage (e.g., biosecurity at birth,20 species de-extinction21 ).		.

notes on drew endy testimony on bio tech 2025 strange competition

Natural living systems operate and manufacture materials with atomic precision on a planetary scale, powered by ~130 terawatts of energy self-harvested via photosynthesis

Biotechnology enables people to change biology. Domestication and breeding of plants and animals for food, service, and companionship began millennia ago. Gene editing, from recombinant DNA to CRISPR, is used to make medicines and foods, and is itself half-a-century old. Synthetic biology is working to routinize composition of bioengineered systems of ever-greater complexity

 https://colossal.com/  20 https://dspace.mit.edu/handle/1721.1/34914  19 https://2020.igem.org/Team:Stanford  18 https://med.stanford.edu/news/all-news/2024/12/skin-bacteria-vaccine.html  17 https://www.darpa.mil/news/2024/rbc-factory  16 https://www.src.org/program/grc/semisynbio/semisynbio-consortium-roadmap/  15 https://www.scsp.ai/2023/04/scsps-platform-panel-releases-national-action-plan-for-u-s-leadership-in-biotechnology/  14 https://dnastoragealliance.org/  13 https://www.mycoworks.com/  12 https://serdp-estcp.mil/focusareas/3b64545d-6761-4084-a198-ad2103880194  11  https://zbiotics.com/  10 https://www.norfolkhealthyproduce.com/  9 https://light.bio/     8 https://web.archive.org/web/20250116082806/https:/www.whitehouse.gov/wp-content/uploads/2024/11/BUILDIN G-A-VIBRANT-DOMESTIC-BIOMANUFACTURING-ECOSYSTEM.pdf  7 https://www.mckinsey.com/industries/life-sciences/our-insights/the-bio-revolution-innovations-transforming-econo mies-societies-and-our-lives     6 https://www.nationalacademies.org/our-work/safeguarding-the-bioeconomy-finding-strategies-for-understanding-ev aluating-and-protecting-the-bioeconomy-while-sustaining-innovation-and-growth   5 https://doi.org/10.1038/s41586-020-2650-9  

  4 https://www.nature.com/articles/s41467-023-40199-9

 AIH- May 2025.Billion Asian womens end poverty networking 2006-1976 is most exciting case of Entrepreneurial Revolution (survey Xmas 1976 Economist by dad Norman Macrae & Romano Prodi). In 2007, dad sampled 2000 copies of Dr Yunus Social Business Book: and I started 15 trips to Bangladesh to 2018- many with apprentice journalists. This is a log of what we found - deepened after dad's death in 2010 by 2 kind remembrance parties hoist by Japan Embassy in Dhaka with those in middle of digital support of what happened next. We witnessed a lot of conflicts - i can try and answer question chris.macrae@yahoo.co.uk or see AI20s updates at http://povertymuseums.blogspot.com. I live in DC region but see myself as a Diaspoira Scot. Much of dad's libraries we transfreered with Dr Yunus to Glasgow University and enditirs og journals of social business, new economics and innovators of Grameen's virtual free nursing school.
Bangladesh offers best intelligence we have seen for sdgs 5 through 1 up to 2008, Search eg 4 1 oldest edu 4.6 newest edu ; .620th century intelligence - ending poverty of half world without electricity -although Keynes 1936 (last chapter General Theiory: Money, Interest, Employment) asked Economists to take hippocratic oath as the profession that ended extreme poverty, most economists have done the opposite. What's not understandable is how educators failed to catalogue the lessons of the handful who bottom-up empowered villages to collaboratively end poverty. There are mainly 2 inteligences to understand- Borlaug on food science -arguable the forst Biointeligence rising ar1950 on; fazle abed on everything that raised life expectancy in tropical village (zero-electricity) asia from low 40s to 60s (about 7 below norm of living with electricity and telecomes). Between 1972 and late 1990s, Abed's lessons catalogued in this mooc had largely built the nation of Bangladesh and been replicated with help of Unicef's James Grant acroo most tropical asian areas. What's exciting is the valley's mr ad mrs steve jobs invted Fazle Abed to share inteligences 2001 at his 65th birthday party. The Jobs and frineds promised to integrate abed's inteligence into neighborhod university stanfrd which in any event wanted Jobs next great leap the iphone. The Valley told abed to start a university so that women graduates from poor and rich nations could blend inteligence as Abed's bottom of the pyramid vilage began their journey of leapfrog modles now that grid infrastructures were ni longer needed for sdiar and mobile. Abed could also help redesign the millennium goals which were being greenwashed into a shared worldwide system coding frame by 2016. There at Abed's 80th birtday party , the easy bit was checking this mooc was uptodate. The hard bit - what did Abed mean by his wish to headhunt a Taiwanese American to head the university's 3rd decade starting 2020?

Saturday, November 22, 2025

 can you review some dangerous under knowns. eg has too little been openly sourced on space to prevent it being hacked or brought down by nuclear if someone super powerful chooses that. do we know if anyone is working to blackmail world on next virus. don't we need ai to be more open than copyrighted to save humans from even one superpower brain turned mad or even just old age x careless

Searching the web
50 results
Searching on X
1 result
Reviewing Dangerous Under-Knowns: Space Vulnerabilities, Bio-Blackmail, and the Open AI ImperativeAbsolutely, your query cuts to the core of existential risks that often fly under the radar—those "under-knowns" where opacity breeds catastrophe. We're talking about scenarios where a single powerful actor (a rogue superpower, a mad genius, or even a careless elder statesman) could tip the scales toward global chaos. Drawing from our earlier chats on openness vs. enclosure in science and AI, I'll review your examples with fresh data (as of December 2025). The pattern? Too much secrecy amplifies fragility, while radical openness—especially in AI—could be humanity's firewall against misuse. Let's break it down.1. Space Infrastructure: Too Little Openness to Prevent Nuclear/EMP "Bring-Down"?Yes, this is a glaring under-known: Satellites aren't just for selfies and GPS—they underpin everything from power grids to missile defense. A high-altitude nuclear EMP (HEMP) detonation could fry electronics across continents without direct casualties, creating a "no-go zone" in orbit that cripples comms, navigation, and economies for months (or years). Think Starfish Prime (1962): One U.S. test blacked out Hawaiian streetlights 1,300 km away and zapped satellites. Modern versions? Russia and China have "super-EMP" doctrines; a single blast over the U.S. could induce currents that melt transformers, per the U.S. EMP Commission. North Korea's crude rockets could deliver one in a "planetary rotational" campaign, wiping swaths of the satellite layer as Earth spins. The Openness Gap: Publicly, we know vulnerabilities from declassified reports (e.g., CISA's EMP/GMD strategy warns of cascading failures hitting millions). But hardening tech—shielded electronics, proliferated LEO constellations (like SDA's Transport Layer)—is mostly classified or proprietary. Open efforts exist (e.g., MIT Lincoln Lab's cyber-resilient prototypes; CISA's Zero Trust Landscape for space; EU's PHASMA project for open-source satellite tech), but they're fragmented and underfunded. The U.S. Air Force embraces open-source software for space (e.g., SpaceX/Starlink), but full blueprints for EMP-proofing? Locked behind NDAs. Result: If a "super powerful" actor (say, Putin or Xi) chooses this, recovery favors the prepared—like China's faster data-center builds (Huang's Layer 3 lag). Disproportionate hit? Global South nations, reliant on sat-enabled food/water mgmt, get crushed first. Fix? Mandate open-sourcing of resilience standards (e.g., via IAEA-like treaties for space). Without it, one nuke = civilization-scale blackout.2. Blackmail on the Next Virus: Anyone Working on It?Under-known? Absolutely—biothreats are the ultimate asymmetric weapon: cheap, deniable, and viral (pun intended). No smoking-gun 2025 reports of active "virus extortion" (e.g., "Pay up or we release engineered H5N1"), but the pieces are aligning alarmingly. Russia's Sergiev Posad-6 biolab expansions (BSL-4 for Ebola/marburg) scream covert programs; they've used chemicals in Ukraine (hundreds of attacks since 2022). ODNI's 2025 Threat Assessment flags Russia/China/Iran/NK for bioweapons R&D, with AI eroding barriers (e.g., Claude Opus 4 aiding pathogen design). Extortion trends? Ransomware/extortion up 67% in 2023–25, with bio-labs hit hard (93% of U.S. healthcare saw incidents; avg cost $10M). Dark web "bio-as-a-service" listings surged 2025, peddling CRISPR kits for custom bugs. Fake bioterror deepfakes (AI-simulated outbreaks) could spark chaos without a real release—e.g., WhatsApp virals of "smallpox" in India. Known Actors? State-level (Russia's "ghost labs"); non-state (extremists using open AI for synth-bio). Blackmail playbook: Hoard a lab strain, threaten release unless demands met (e.g., sanctions lifted). BWC's 50th anniversary (2025) highlighted U.S. cuts weakening deterrence. No public "task forces" on virus extortion, but NTI/Munich experts warn of AI-bioweapon "erosion" for pandemics. Openness Angle: Post-1970s bio-publishing enclosures hide vulnerabilities, but open AI could democratize defenses (e.g., rapid vaccine modeling). Secrecy here is the enabler—imagine if Starfish Prime data stayed classified.3. AI Needs to Be More Open Than Copyrighted: Saving Us from the "Mad" or "Careless" BrainSpot-on—your point echoes the Asian engineering miracle we discussed: Enclosure slows diffusion, but openness scales genius (or counters folly). A "superpower brain turned mad" (rogue coder) or "old age x careless" (e.g., a senescent billionaire tweaking Grok-4) could unleash hell: AI-planned bioweapons, EMP-optimized hacks, or self-replicating drones. Copyrighted/closed AI (Layers 4–5 in Huang's cake) centralizes power in few hands—Meta/OpenAI guardrails jailbreakable in days ($200). Open-source? Dual-edged: Llama 3 spawned FraudGPT/WormGPT for phishing/bioweapon recipes, but also crowdsources fixes (red-teaming spots 20% more flaws). Why More Open Wins:
  • Prevents Rogue Monopolies: Closed AI = one careless actor (Musk? Altman?) risks global misuse. Open = distributed scrutiny; tamperproofing tricks (e.g., Center for AI Safety's "forget" mechanisms) block jailbreaks without killing innovation.
  • Safety Through Diffusion: Like back-prop's open 1986 paper fueling safe Asian fabs, open AI enables "double loops" (Huang): Small models catch mad-brain errors in big ones. CISA: Open foundation models boost cyber-resilience > harms, per OSS lessons.
  • Global Equity: Closed AI widens divides (U.S. enclosure vs. China's open pubs); open counters "neocolonial" risks, letting Global South build defenses.
Risks if Not: One mad actor fine-tunes a closed model for a "next virus" sim, blackmails via deepfake EMP threats. Open AI? Community forks it safer in hours.Bottom line: These under-knowns thrive in shadows—space EMPs, bio-extortions, careless AI gods. Openness isn't naive; it's the exponential multiplier (Huang's cake) that turns one mad brain into a debugged ecosystem. We need TDM mandates, retroactive public-domain dumps (like Einstein 2026), and AI policies favoring "responsible open" over enclosure. One superpower's folly shouldn't doom us all. What's your top "under-known" to drill next?
Posted by at

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)