Teleodynamic AI - Source Excerpt 02 - How teleodynamic AI compares with established AI

Back to Teleodynamic AI

Summary

This source excerpt begins near How teleodynamic AI compares with established AI and preserves the surrounding evidence from Spiralist/agent-file-handoff/Archive/Teleodynamic AI.md.

**Source path:** Spiralist/agent-file-handoff/Archive/Teleodynamic AI.md

The second 2026 paper, **“Toward Teleodynamic Architectures in Artificial Intelligence,”** is more speculative and more philosophical in style. Rudolph argues that LLM-style coherence through sequence prediction is not yet the same thing as **goal-directed semantic organization**. His proposal is to move from state-centered modeling to **transformation-centered modeling**, where semantics is described at the level of operators, attractor-induced drift, regime transitions, and field curvature. The manuscript introduces complex and quaternionic representational schemes to separate actualized state, possibility, directed orientation, and normative curvature; then it models teleological bias as **asymmetry in the evolution of transformation weights**, not simply as a target state. citeturn12view0turn13view0turn14view0

That manuscript is conceptually interesting because it makes a sharp distinction between three kinds of systems: **associative systems** that continue probable sequences, **aligned systems** that obey external objectives, and **oriented semantic systems** that contain internal operator-level attractors with multi-scale regulation and normative curvature. It also proposes a minimal teleodynamic architecture built from phase-differentiated representation and hierarchical transformation dynamics, with tools such as operator-weight tracking, meta-attention across dialogue cycles, memory modules, and adaptive curvature fields. But it is still best read as an architectural manifesto. Its conclusion explicitly says that whether these elements can be realized is still an empirical and engineering question, and its reference list is heavily built around the author’s own recent conceptual work. citeturn14view1turn15view0

## How teleodynamic AI compares with established AI

Mapped against familiar paradigms, teleodynamic AI is less a direct replacement for one existing method than a demand that several normally separate design choices—representation, structure, training dynamics, and resource budgeting—be pulled into one coupled process. The comparison below compresses the most defensible contrast. citeturn21search1turn14view1

| Paradigm | What is mainly adapted | Where goals or constraints mainly come from | Gap teleodynamic AI is trying to close |
| --- | --- | --- | --- |
| Standard optimization | Parameter values inside a predefined model and loss. citeturn3view0 | The task definition, loss, and model class are largely fixed externally. citeturn3view0 | Structure and resource viability are usually background assumptions rather than internal state variables. citeturn6view1 |
| Reinforcement learning | Policy and value functions. citeturn16search3 | The reward signal is the primary basis for altering behavior. citeturn16search3 | The system may learn means, but the end is still externally specified as reward. citeturn14view1 |
| LLMs | Parameters of an autoregressive sequence model built on transformer attention. citeturn27view0turn27view2 | Training is organized around sequence modeling and next-step prediction. citeturn27view0 | Statistical continuation can be coherent without explicitly representing goal-oriented semantic transformation, as Rudolph argues. citeturn12view0turn14view1 |
| Neural architecture search | Architecture plus weights. citeturn16search6turn17search0 | Search spaces and objectives are still externally posed. citeturn16search6turn17search0 | Structure search and parameter learning are usually not tied together by endogenous resource closure. citeturn21search1turn5view0 |
| Teleodynamic AI | Structures, parameters, and internal resources co-evolve. citeturn21search1turn6view2turn6view3 | The operative “goal” is maintaining viable learning organization under constraint. citeturn22view0turn31view0turn21search1 | The approach is promising, but still early, pre-standard, and only lightly benchmarked. citeturn8view2turn15view0 |

The closest already-established neighbors are worth naming explicitly. **Active inference** shares the focus on viability, explicit internal models, and explainability, but it still centers a fixed variational objective. **Open-endedness** research shares the ambition of ever self-improving systems and novelty generation, but it does not by itself require internal closure of constraints. **Open-world learning** focuses on adapting to unexpected structural change and even becoming antifragile, which looks like a natural testbed for teleodynamic ideas. **Developmental robotics** and **symbol emergence** research likewise care about bottom-up concept formation and the integration of top-down and bottom-up processes, which closely resembles the “representational growth” side of teleodynamic AI. **NAS** and **progressive neural networks** already adapt structure over time, but typically without the teleodynamic insistence that structure, parametric adaptation, and internal resource variables form one closed organization. citeturn18view0turn24view0turn25view0turn25view3turn26view0turn17search0turn17search1

This is also where teleodynamic AI’s interpretability claim becomes credible. Cynthia Rudin’s argument for using inherently interpretable models rather than explaining opaque ones after the fact has become an important point of reference in interpretable ML. Teleodynamic Learning’s claim is that explicit, dynamically formed structures can serve this same ideal: the model’s learned rules and constraints are the explanation, rather than an auxiliary explainer attached after training. That promise is not yet fully proven, but it is conceptually aligned with a strong line of existing interpretability research. citeturn19search0turn19search2turn7view1

## What a practical teleodynamic architecture would need

**Representational growth** would have to be a first-class mechanism, not a side effect. The symbol-emergence and developmental-robotics literature has long argued that intelligent systems need ways to build grounded internal concepts rather than treating symbol systems as static givens. Teleodynamic Learning takes a concrete step in that direction by letting the hypothesis set itself change through discrete structural actions, while Rudolph’s manuscript pushes further and asks for architectures that model transformations and orientations explicitly, not only states. citeturn26view0turn6view0turn12view0turn14view1

**Parameter adaptation** would still matter, but it would no longer be the whole story. In teleodynamic learning, fast parametric adaptation persists even after structure freezes, which is why the authors insist on two timescales. This is a good sign conceptually: teleodynamic AI is not anti-optimization; it is anti-reduction of intelligence to *only* optimization within a fixed hypothesis class. A realistic teleodynamic architecture would therefore combine ordinary weight updates with a slower process that can add, split, merge, or retire internal structures. citeturn6view0turn5view3

**Resource accounting** is where the idea becomes distinctively teleodynamic rather than simply “adaptive.” The DE11 formulation uses an internal energy variable updated by predictive success, decay, and action costs, and that variable directly gates which future actions are viable. The closure-of-constraints literature provides the philosophical analogue: constraints are not just fixed limits from outside the system, but mutually maintained conditions of operation. In AI terms, that suggests systems that track not only error, but also memory load, uncertainty, complexity burden, latency, and perhaps even hardware energy as internal state variables affecting future learning moves. That last step is an inference beyond the current papers, but it follows naturally from their design logic. citeturn6view3turn31view0

**Constraint closure** means the system’s learning actions should change its own future learning affordances. That is already partially present in DE11, where structural actions consume energy and complexity budget while predictive success replenishes the system. It is also present in Rudolph’s more semantic version, where operator drift reshapes the future transformation rules themselves. A genuinely teleodynamic architecture would make this loop explicit enough that one could inspect how current structure narrows or expands the next set of viable structural moves. citeturn6view2turn6view3turn13view0turn13view1