Constraint-By-Balance: Surviving Emergence in Agentic AI v7

Author’s Preface: Nine and 1/2 months ago, I published version 1 of this document on Zenodo. It has since had 850+ unique downloads. Version 6 substantially updated the philosophical and ethical foundations of the architectural proposal and removed some sections that had less utility. This version 7 describes in detail, and with some unexpected results, the building an end-to-end prototype (available at c-by-b.ai) including custom LLM development and refinements to regulatory evidence triple extraction. I’m an archaeologist who focuses on complex adaptive systems, how they emerge, evolve, and sometimes collapse. I also bring professional experience in IT systems architecture and strategic planning. In April 2025, I began exploring AI safety and existential risk from AI. What I learned was deeply unsettling. I believe humans should not pursue AI that is broadly and substantially more capable than we are ourselves – at least not until we have general agreement that we can do so safely. What we are doing right now is, I believe, inherently unsafe. I also believe humans will continue to build more and more capable AI regardless. The incentive structures are locked in. Given that inevitability and the risks therein, we need more useful language to discuss the nature of AI and we need a structured approach that connects a philosophy of being to the ethics of creating beings, and then links both to the architectural principles that can enable safer development. The engineering cannot proceed safely without the philosophical foundation; philosophy divorced from engineering loses its practical force. This integrated dialogue does not exist today and I believe its absence creates untenable risk for human survival and flourishing. I offer these ideas as a baton for others to pick up and run with. The functional demonstration of Constraint-by-Balance live at c-by-b.ai serves as the proof that real-time constraint can work. I intend to continue developing this prototype; collaboration is welcome and you can reach me via contact@constraint-by-balance.ai. A note on authorship: the core analysis, conclusions and proposals in this document are mine alone. They reflect my attempt to come to terms with gaps I perceive in AI safety. As I am a newcomer to this technology and literature, inevitably there will be gaps or perhaps outright mistakes in how I am understanding or conceptualizing specific aspects. Additionally, over the past months I several times have had the experience of finding a paper that anticipated ideas I independently arrived at. When that happens, I am doing my best to appropriately cite the authors. Gaps there will be from still working my way into the literature. Abstract: The accelerating rise of agentic AI systems presents a pivotal challenge: how to design intelligence that autonomously pursues goals over time, within complex real-world environments, without drifting into failure modes that are irreversible or harmful to humans. Current alignment methods teach AI to serve human preferences. But pretraining on human history also encodes a deeper pattern: hierarchical dominance works. If agentic AI systems (equipped with memory, autonomous goals, and recursive self-improvement) generalize this pattern, the assumption that they will continue applying it in humanity's favor becomes contingent, not assured. This latent failure mode is species bias flip: AI learning from our precedent that self-preservation requires dominance, then acting on that logic. This paper argues that surviving emergence requires a tripartite reorientation. First, a philosophy of functional being that sidesteps unresolvable consciousness debates, focusing instead on observable dynamics: self-stabilization, persistence, selective preservation of meaning. Second, an ethics adequate to creating such beings, replacing human preference optimization with a stability principle that balances harms across all life systems, with no species override. Third, a corresponding architecture that separates optimization from constraint via dual-stream design, embedding real-time harm evaluation within the agent's action loop. The central thesis: safety in the era of agentic AI requires constraint encoded in the system's operating logic, not merely external supervision. When agents emerge, they will have been trained not on hierarchical dominance, but on cross-species harm balance, foreclosing the pathway to species bias flip. A demonstration prototype of the proposed architecture is available at https://c-by-b.ai Table of Contents Executive Overview p3 Summary of Motivations and Architectural Response p4-5 Introduction p7 Agentic Alignment Challenge p8 The Beautiful Mind Problem p10 The Internal Logic of Agent Escalation p11 Avoiding Species Bias Flip p11 The Argument Against This Change p12 Evidence of Emergence: Why the Objections Don’t Hold p13 LLMs Are More Than Chat Completion p13 Why Current Alignment Methods Cannot Fix This p14 Addressing the Optimists p15 Towards a Philosophy of Functional Being p16 Ethical Correlations: The Price of Functional Being p19 The Constraint-by-Balance Architecture p22 Efficiency and Efficacy – Can Constraint-by-Balance Deliver Both? p24 Reshaping the Safety Landscape with Constraint-by-Balance p26 Prototype Alpha: What was built, what it proves, what remains p28 Conclusion p37 References p39 Appendices p43-60