Engineered Thinking

Autonomous agents need shared, verifiable vocabulary: labels that compress coordination without hiding semantic drift. Sema turns content-addressed behavioral contracts into words in natural language — each simultaneously a word and a cryptographic proof. A Pattern Card canonicalizes a behavior’s invariants, preconditions, and failure modes into a hash-backed identifier that ordinary prose can carry. A bootstrap vocabulary of 452 patterns shows 22.6× mean token compression across the library.

Understanding — the movement from confusion to clarity — was always ephemeral. When AI reasons in tokens, it becomes directly storable in the medium where it occurs. Rather than indexing documents or extracting user facts — the two dominant paradigms in AI memory — the Understanding Graph captures the cognitive process itself: tensions, hypotheses, belief revisions, dead ends. Not what the AI concluded, but how it understood.

Most alignment methods intervene after capabilities have formed. Entangled Alignment belongs to a newer family of work that moves safety-relevant learning into pretraining, but proposes an unusually structural version of that idea. One continuous Reader processes arbitrary source works chronologically, carrying the same evolving, provenance-linked Understanding Graph from earlier works into later ones. At every selected Thought Moment, each generated thinking block opens with the full, verbatim Reader Core before continuing into source-specific evaluation and revision. The safety-relevant signal is therefore attached to capability-bearing material, supported by persistent memory, and anchored by the same recurrent orientation across the corpus—not confined to a separate collection of safety documents. The paper defines three hypotheses: whether reader traces improve capability and safety-relevant evaluation (H1), whether graph conditioning improves those traces (H2), and whether the recurrent Core creates a stable but revisable orientation (H3). Two case studies demonstrate the Teacher pipeline, but no Student has yet been trained. The distinctive empirical bet is the combination of persistent graph memory and exact Core recitation. Its long-run aim is inheritance rather than armor: making the orientation part of what capable systems learn and potentially pass to their successors.

Ask an LLM to “be creative” and it converges on the same archetypes — the Median Trap. This paper compares eight methods for inducing structural diversity in a controlled experiment (N=196): Semantic Tabu accumulates constraints, the Studio Model pairs a generator with a strict taxonomist, and the Orthogonal Insight Protocol derives mechanisms from alternative physics. Under constraint pressure the system showed emergent metacognition — repairing its own taxonomy and commissioning research into regions it hadn’t explored — and produced structural novelty that no monolithic model reaches. The boundary does the creative work.

Existing frameworks decompose tasks. This paper decomposes concepts — the persistent structure of what a domain is made of. Each concept becomes a solver node behind one five-surface contract, so a leaf and a thousand-node subtree are indistinguishable to their caller: specialists all the way down. In a prototype of 100 problems across 20 domains, concept-based routing produced a shared graph of 456 nodes with 64% reuse — the structural precondition, not yet the improvement it predicts. If decomposed solving beats the conventional approach at matched compute, and independent attempts converge on the same concepts, the result is an internet of reasoning: a shared substrate where you post a problem rather than fetch a page.

Language models are lazy optimizers: if a shortcut to the answer exists — retrieval, memorization — the gradient will reinforce it over reasoning. Temporal Hindsight Learning treats the knowledge cutoff as a curriculum tool rather than a defect: a Teacher with hindsight works backward to the causal signals that were available before the outcome; the Student, frozen in the past, must derive them rather than retrieve them. In a pilot on unseen 2025 events, a 70B Student improved reasoning quality by 20% over its base model and approached its frontier Teacher in prediction accuracy. Blindness is the teacher.