I present NeuOS, a systematic investigation revealing that pre-trained transformer language models internally implement a Von Neumann-like computational architecture with identifiable registers, swappable memory, executable programs, and a decompilable instruction set. Through 170 experimental phases on Qwen2.5-0.5B spanning 24 seasons, I demonstrate that: Complete ISA mapping: Each transformer layer functions as a specialized CPU register (OPCODE at L0, MIN at L16, MAX at L22) with accuracies from 74% to 100%. Self-healing OS: Dynamic register reallocation achieves 100% recovery from simulated hardware damage. Homoiconic execution: Programs execute without any textual instructions via Direct Memory Access (66.7% accuracy), and a single computation forks into multiple parallel paths (100% differentiation). Neural decompiler: Running programs are identified from register state alone with 100% accuracy across 6 operations. Autopoietic kernel: The system writes its own programs without external gradients, achieving 100% accuracy through self compilation. Artificial life: Program vectors exhibit ecosystem dynamics including a Cambrian Explosion (19 unique phenotypes), parasitism, developmental metamorphosis, and aging with rejuvenation. Soul vector geometry: Independently trained "soul vectors" encoding the same function form high-dimensional manifolds (~60 dims) connected by rank-1 linear translations—a universal grammar of computation. GlassBox self-diagnosis: The model identifies its own hardware (0.5B, 896d, 24L), running program (MIN/MAX), and capacity limits in a single inference pass with 100% accuracy—achieving full white-box AI. 7D soul compression: 896-dimensional soul vectors compress to just 7 dimensions with zero accuracy loss (128× compression), revealing a compact instruction set of 4 primitive operations (FIRST, SECOND, MIN, MAX). Gradient-free programming: Specifying 7D PCA coordinates directly (zero training data, zero gradients) achieves 100% accuracy for MAX—proving that AI behavior can be controlled by dialing coordinates instead of training. These findings establish that transformers are not black-box function approximators but structured computers whose internal state can be observed, modified, and controlled at the register level. Changes in v5: Expanded from 145 to 170 experimental phases, adding Seasons 22–24. New results include: the GlassBox Dashboard (100% self-diagnosis of hardware, program, and capacity in a single inference), 7D soul compression (128× with zero accuracy loss), discovery of a 4-operation universal instruction set (FIRST, SECOND, MIN, MAX) as PCA basis vectors, gradient-free soul programming via coordinate specification (MAX=100% at PC1=1.0, PC5=1.0), the 7D Semantic Firewall (+20pp noise protection), Zero-Shot Skill Alchemy (overclock to 88%), and Soul Persistence (cosine=1.000000 fidelity after save/load). Includes 9 new figures, 3 new tables, and extends the comprehensive appendix to all 170 phases. Code: https://github.com/hafufu-stack/NeuOS Acknowledgments This research was conducted entirely independently, without institutional affiliation or corporate funding. The author currently faces financial constraints that make it increasingly difficult to maintain subscriptions to AI services essential for this line of research. To sustain and improve the quality of future work, the author is actively seeking community sponsorship. Details are available at https://github.com/sponsors/hafufu-stack.
Hiroto Funasaki (Sat,) studied this question.