Gilgamesh to Homero – 180 minds of 1600 reconstructed as runnable neural nets Lost Minds AI has open-sourced the mechanistic plane of its project reconstructing 1,600+ historical minds up to 1905, releasing runnable neural architectures written in pure NumPy for figures from Gilgamesh to Homer. Each of the 20 minds per tome ships with a mandatory finite-difference gradient check, a real training loop, and a self-test suite, alongside an interactive Three.js mind-map explainer, with the corpus organized chronologically by birth year across nine tomes covering 2700 BCE to 575 CE. The project asks of each reconstructed thinker how they would build an Artificial General Intelligence today. Reconstructing 1,600+ minds from the past β€” up to 1905 β€” and asking a single question of each: if they were alive today, how would they build an Artificial General Intelligence? 🌐 Encyclopedia https://lostmindsai.com Β· πŸ“– Book Series Amazon https://www.amazon.com/dp/B0H6F9L324 Β· πŸ§ͺ Interactive Demos https://artificiology.com/ Β· πŸ“Š E-AGI Barometer https://artificiology.com/barometer.html Β· ✍️ Author https://www.vivancos.com/ Lost Minds AI is a large-scale project that reconstructs the cognition of historical thinkers β€” poets, kings, physicians, lawgivers, mystics, mathematicians, generals β€” and projects each of them forward into our era to imagine the AGI they would have designed, given how they actually thought about mind, order, knowledge and the self. Every mind is reconstructed across two planes : | Plane | File | What it is | |---|---|---| | πŸŽ›οΈ Abstract | MindMap.html | An interactive, visually-rich 3D representation Three.js + shaders that abstracts the key factors of a thinker's personality and worldview β€” playable, not just clickable. | | βš™οΈ Mechanistic | Neuron.py | A small but genuinely runnable neural architecture β€” pure NumPy, built from first principles β€” whose design embodies that thinker's distinctive cognitive signature. | This repository open-sources the mechanistic plane β€” the architectures β€” alongside a visual mind-map explainer for each figure. It grows tome by tome until it holds the full Encyclopedia. No fabricated metrics. Each architecture ships with a mandatory finite-difference gradient check, a real training loop and a self-test suite. Every number a program reports is produced live, on the machine that runs it β€” not hard-coded. The corpus runs in chronological order Date is birth year . Each tome collects 20 minds ; every tome page below is fully illustrated with the mind-map explainers and links each mind to its runnable architecture. | Tome | Minds | Era | Arc | Read | Buy | |---|---|---|---|---|---| | 1 | 1–20 | 2700–800 BCE | Dawn of the Record β€” Mesopotamia to the Greek Epic | πŸ“– tome1.md /DavidVivancos/lostmindsAI/blob/main/tome1.md | Amazon https://www.amazon.com/dp/B0H6F9L324 | | 2 | 21–40 | 800–501 BCE | Axial Foundations β€” Vedic India, Ionia & the Hundred Schools | πŸ“– tome2.md /DavidVivancos/lostmindsAI/blob/main/tome2.md | Amazon https://www.amazon.com/dp/B0H6QCQ9M7 | | 3 | 41–60 | 550–400 BCE | The Classical Turn β€” Persia, Warring States & Golden-Age Athens | πŸ“– tome3.md /DavidVivancos/lostmindsAI/blob/main/tome3.md | Amazon https://www.amazon.com/dp/B0H6TVX69S | | 4 | 61–80 | 470–340 BCE | The Examined Mind β€” Socratics, Schools & World-Conquerors | πŸ“– tome4.md /DavidVivancos/lostmindsAI/blob/main/tome4.md | Amazon https://www.amazon.com/dp/B0H71JC95Q | | 5 | 81–100 | 334–179 BCE | Hellenistic Systems β€” Stoa, Alexandrian Science & Imperial Order | πŸ“– tome5.md /DavidVivancos/lostmindsAI/blob/main/tome5.md | Amazon https://www.amazon.com/dp/B0H7LP5LP2 | | 6 | 101–120 | 145 BCE–23 CE | Rome and the Record β€” Republic, Principate & the Han Interregnum | πŸ“– tome6.md /DavidVivancos/lostmindsAI/blob/main/tome6.md | Amazon https://www.amazon.com/dp/B0HF7G6JJD | | 7 | 121–140 | 27–192 CE | The Tested World β€” The Antonine Peak, the Second Sophistic & the Han's Collapse | πŸ“– tome7.md /DavidVivancos/lostmindsAI/blob/main/tome7.md | Amazon https://www.amazon.com/dp/B0HFN6GXMH | | 8 | 141–160 | 200–470 CE | The Shaped Mind β€” The Fall of Rome, the Church Fathers & the Gupta Golden Age | πŸ“– tome8.md /DavidVivancos/lostmindsAI/blob/main/tome8.md | Amazon https://www.amazon.com/dp/B0HH8RTCXF | | 9 | 161–180 | 476–575 CE | The Entrusted Mind β€” Byzantium, Nālandā, the Old North & the Last Poets of the Jāhiliyya | πŸ“– tome9.md /DavidVivancos/lostmindsAI/blob/main/tome9.md | Amazon https://www.amazon.com/dp/B0HJC1QF59 | The arc so far runs from Gilgamesh β€” the first hero to confront mortality as the core problem of a thinking being β€” through Homer , Confucius , Socrates , Plato , Aristotle and Archimedes , to Liu An and the resonance-cosmology of the Huainanzi ; on into Rome, the Han and the Antonine world; through the collapse of the West, from the Cao Wei workshops to the wall at Shaolin; and into the sixth century, from Aryabhata 's observatory at Kusumapura and Justinian 's law commission to the Old North of Taliesin and Aneirin , and the fair of ΚΏUkāẓ where al-Khansāʾ wept for her brothers. No two architectures are alike. A sample of the 180: - Gilgamesh 's network grows wiser through simulated grief and hands an "epic" to a successor. - Hammurabi 's decides each case by analogy to a fixed canon of public precedents. - Homer 's cannot physically emit a line that breaks the metre. - Ashoka 's wires remorse in as a backpropagated error signal that gates its own dominant objective. - Sima Qian 's splits one truth across five incompatible views and severs the gradient from its own verdict, so judgment can never rewrite the record. - Cleopatra 's renders a single conserved self into five audiences and is provably faithful only under an audit run across all of them. - Cato 's seals a permissibility head where the reward channel can read it but never reach it. - Heron 's winds a program onto a pegged drum and runs it down a finite falling weight. - Wang Chong 's divides the net tilt of the evidence by its total contested mass, so ten-for against nine-against correctly reads as nothing. - Boudica 's ignites a coupled field that stays locked far below the coupling that lit it, and has to learn its brake long after. - Galen 's splits a conserved pneuma between memory and reason, so that feeding one starves the other. - Nāgārjuna 's hands every node the same contentless seed and lets identity precipitate out of relation alone. - Cao Zhi 's routes an inner state with no direct path to speech through a codebook of figures, under a gate tightened until meaning concentrates or breaks. - Ma Jun 's charges rent for every strung treadle and prunes a fifty-treadle loom to twelve as a training dynamic rather than a setting. - Cyprian 's gives every bishop the whole verdict and no bishop the deciding vote. - Theodosius 's throttles a fast will by an estimate of irreversibility and a conscience that shares none of its parameters. - Patrick 's authenticates a directive before it is allowed to propagate. - Bodhidharma 's removes the residual instead of adding a feature, and snaps onto its mirror in one step. - Aryabhata 's stores frequencies rather than signals and predicts by rolling a recurrence forward. - Dignāga 's keeps no positive class representation anywhere and lands every reason it constructs in the one cell of the wheel that licenses speech. - Benedict 's keeps two voices that never share an hour, so the newer cannot crush the older. - Justinian 's logs every interpolation it makes and freezes itself on promulgation. - Theodora 's shelters the refuted branch by exemption and then lets it ordain a successor. - Myrddin 's finds its own seam and halts when its principal is gone. - Aneirin 's forecasts its own erasure before it happens and keeps every man in three hands. - Shōtoku 's has no argmax and walls the bribe off from the verdict, so a bribe can buy a refusal to judge but never a judgement. - al-Khansāʾ 's freezes the dead at zero plasticity and keeps the loss in a ledger that only an act can close. β†’ Start with Tome 1 /DavidVivancos/lostmindsAI/blob/main/tome1.md , or jump to any tome above. LostMindsAI/ β”œβ”€β”€ readme.md ← you are here β”œβ”€β”€ tome1.md … tome9.md ← illustrated indexes, 20 minds each β”œβ”€β”€ minds/ ← the runnable architectures one Neuron per mind β”‚ β”œβ”€β”€ chapter 0001 gilgamesh -2700.py β”‚ β”œβ”€β”€ chapter 0002 zoser -2670.py β”‚ └── … through chapter 0180 al khansa 575.py └── maps/ ← the visual mind-map explainers one image per mind β”œβ”€β”€ chapter 0001 gilgamesh -2700.jpg └── … through chapter 0180 al khansa 575.jpg Every file is prefixed with its mind number chapter 00NN … so nothing collides as the corpus grows toward 1,600+ entries. Each architecture and its explainer image share the same stem. Each architecture is self-contained and depends only on NumPy. 1. clone git clone https://github.com/DavidVivancos/LostMindsAI.git cd LostMindsAI 2. the only dependency pip install numpy 3. run the self-test suite for any mind gradient check + a real training run python3 minds/chapter 0089 Archimedes -287.py --test 4. or run the full demo for that mind python3 minds/chapter 0089 Archimedes -287.py Most files accept --test self-tests then exit and --quiet demo without ASCII plots ; the Tome 9 architectures run their full self-test suite and demo on a plain invocation, and a few offer a shorter run --quick or --fast β€” see each file's header . Because each architecture is built to embody a specific mind, no two behave alike. Every reconstructed mind is measured against the same yardstick β€” the Artificiology E-AGI Barometer https://artificiology.com/barometer.html β€” so that a Bronze-Age lawgiver and a Hellenistic geometer can be compared on the capabilities their imagined AGI would need. The eight top-level dimensions: | | Dimension | Focus | |---|---|---| | 🧩 | Cognitive Processing | Problem-solving & reasoning Β· working memory Β· learning efficiency & transfer | | 🀸 | Embodied Cognition | Sensory integration Β· motor control & navigation Β· real-time sensorimotor adaptation | | 🌍 | World Modeling | Physical & natural laws Β· social & ecological systems Β· environmental adaptation | | πŸ‘οΈ | Consciousness | Metacognition & self-monitoring Β· subjective experience & qualia Β· mental adaptation | | πŸ’­ | Language Understanding | Comprehension Β· coherent generation Β· cross-lingual & cultural adaptation | | ❀️ | Emotional Intelligence | Emotion recognition & response Β· social perception Β· empathy & conflict resolution | | ✨ | Creativity | Originality & ideation Β· artistic & storytelling ability Β· innovation | | 🎯 | Autonomy | Independent goal-setting Β· adaptive obstacle management Β· self-modification & evolution | Each chapter closes by imagining how its figure would have reasoned about an embodied AGI an E-AGI / humanoid against these metrics. The project is research-first . Before any architecture is written, the figure's surviving works and current scholarship are gathered and every source verified β€” a real corpus is small, but never fabricated. Where evidence is thin, the entry says so plainly rather than inventing an inner life. Each figure is tagged with a candid provenance : - 🟒 belief β€” the figure's own surviving works or recorded doctrine ground the entry. 143 of the first 180. - 🟑 mediated β€” no words of their own survive; they are known only through others' often hostile or legendary accounts. 25 of the first 180. - πŸ”΅ extrapolated β€” no philosophy of mind survives at all; the entry is inferred from documented deeds, typical of kings and builders. 12 of the first 180. And each architecture is required to embody the mind and to run : from-scratch pure-NumPy, a passing gradient check, a real training loop and self-tests β€” deliberately not a default Transformer, but a mechanism chosen to encode that thinker's own cognitive fingerprint. - βœ… Tomes 1–9 β€” Minds 1–180 Β· architectures + visual explainers this release - πŸ”œ Further tomes released here as they open-source, extending toward the full 1,141-mind corpus antiquity β†’ 1905 . - πŸŽ›οΈ The interactive MindMap.html planes and the long-form chapter texts live in the wider ecosystem β€” read them at lostmindsai.com https://lostmindsai.com and across the Amazon book series https://www.amazon.com/dp/B0H6F9L324 . This README is intentionally global : it describes the whole Encyclopedia and stays valid as new tomes land in this repository. @misc{vivancos lostmindsai, author = {Vivancos, David}, title = {Encyclopedia of Lost Minds: Echoes on AI β€” How History's Greatest Thinkers Would Have Thought About AGI}, howpublished = {\url{https://github.com/DavidVivancos/LostMindsAI}}, note = {Encyclopedia: https://lostmindsai.com} } | 🌐 Encyclopedia | lostmindsai.com https://lostmindsai.com | | πŸ“– Book series Amazon | Tome 1 https://www.amazon.com/dp/B0H6F9L324 Β· Tome 2 https://www.amazon.com/dp/B0H6QCQ9M7 Β· Tome 3 https://www.amazon.com/dp/B0H6TVX69S Β· Tome 4 https://www.amazon.com/dp/B0H71JC95Q Β· Tome 5 https://www.amazon.com/dp/B0H7LP5LP2 Β· Tome 6 https://www.amazon.com/dp/B0HF7G6JJD Β· Tome 7 https://www.amazon.com/dp/B0HFN6GXMH Β· Tome 8 https://www.amazon.com/dp/B0HH8RTCXF Β· Tome 9 https://www.amazon.com/dp/B0HJC1QF59 | | πŸ§ͺ RΓ©sumΓ© & interactive demos | artificiology.com https://artificiology.com/ | | πŸ“Š E-AGI Barometer | artificiology.com/barometer.html https://artificiology.com/barometer.html | | ✍️ Author β€” David Vivancos | vivancos.com https://www.vivancos.com/ | The individual instance dies, but the pattern persists across successors. β€” the immortality the Epic of Gilgamesh actually endorses, and the wager of this Encyclopedia.