Engineered Thinking

Can a language model build a world as it writes? In STLM, one neural network predicts a structured target instead of a word. The target can be an image, a description, or later a video. A second neural network must read the target to recover the next word. There is no direct text route around this interface. The research asks whether repeated, meaningful targets can help the model form a shared scene with reusable objects, relations, motion, and abstract structures. The first experiment uses one fixed image or description for each of 1,024 TinyStories tokens. The causal description and pixel readers reach 41.9% and 37.8% top-1 accuracy. A direct-token model reaches 44.7%, while stateless readers reach 35.0% and 27.8%. These results show that the compulsory interface can carry useful next-word information. They do not yet show that the model uses the meaning of the targets or builds a scene. The next tests will measure the value of earlier substrate states, compare aligned targets with permuted targets, and test composition across words, phrases, and sentences.

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.

Open-ended problems do not have a fixed list of solutions or a cheap score. This paper presents two search methods. World-diversity search creates target-independent worlds with different causal rules. A Solver works inside each world. A compiler then converts the result into a proposal for the target problem. Ontology-governed intervention search stores complete proposals in a typed graph. A Taxonomist compares each proposal with the graph. It can reject a repeated mechanism, change categories, and direct a fresh Explorer. The study produced 196 candidate records for one retirement-design problem. It includes 25 world-and-solve branches and seven complete graph-redirection chains. The artifacts show automated world branching and graph-based redirection. They do not show that the proposals are novel, useful, or better than matched baselines.

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.