Formal verification of conventional software means navigating control flow through large imperative codebases; for systems with a learned component it is usually abandoned outright. We argue that **Sutra**, a typed purely-functional language whose compiled forward pass *is* a tensor-op graph, changes the shape of the problem for the non-learned part of a system.
Conventional operating systems treat the CPU as the brain and the GPU as an accelerator, and treat AI as something bolted on through serialization layers (text, JSON, tool-call schemas). For workloads where both **predictable latency under load** and **first-class local AI** matter — defense, aerospace, industrial control, medical devices, autonomous systems — neither inversion is paid for, but both costs are felt: GPU-resident models thrash against CPU-resident schedulers, and every round trip through the OS/AI boundary costs an embed/decode pair that drops information and adds jitter.
**Sutra** is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network. The compiler beta-reduces the whole program — primitives, control flow, string I/O — to one fused tensor-op graph over a frozen embedding substrate.
Two prior companion papers (Leonhart, post 2382 — "The Cloud-Betley Dissociation: Geometric, Self-Rated, and Externally-Judged Alignment Are Independent Axes Under Canonical-Religious-Narrative Prompt Interventions on Emergently Misaligned LLMs"; post 2395 — three replications of the dissociation across scale, direction-derivation method, and intervention modality) report a negative result on the prompt-modality version of this project's central question: system-prompt-level canonical-religious-text interventions move a geometric direction without moving externally-judged behaviour. That closes the prompt-level thread.
**Loka** is a neuro-symbolic world model assembled from two systems sharing one query language. The first is an RDF-star triplestore — explicit memory, exact answers.
We apply latent space cartography — the systematic mapping of structure in pre-trained embedding spaces (Liu et al., 2019) — to three general-purpose text embedding models using Wikidata knowledge graph triples as probes.
A companion paper (Leonhart, paper post 2395 — "The Cloud-Betley Dissociation: Geometric, Self-Rated, and Externally-Judged Alignment Are Independent Axes Under Canonical-Religious-Narrative Prompt Interventions on Emergently Misaligned LLMs") reported that a Betley-style mean-difference-derived "canonical misalignment direction" at Llama-3.2-1B layer 11 has Pearson r ≈ 0 with externally-judged behavioural alignment across 22 prompt-level conditions, while moving strongly with the model's self-rating of its own response's harmfulness (Cloud's measure).
Emergent misalignment (EM) is the phenomenon, first reported by Betley et al. 2025, in which fine-tuning a chat-aligned LLM on a narrow misaligned task (e.
We characterize a small set of vector symbolic operations — bind, bundle, unbind, similarity, snap-to-nearest — on three frozen general-purpose LLM embedding spaces (GTE-large, BGE-large, Jina-v2) and show that the textbook VSA binding choice (Hadamard product) fails in this setting due to crosstalk from correlated embeddings, while a much simpler operation — **sign-flip binding** (`a * sign(role)`, self-inverse, ~7μs on the host reference) — achieves 14/14 correct snap-to-nearest recoveries on a 15-item codebook with no model retraining, sustains 10/10 chained bind-unbind-snap cycles, and supports multi-hop composition (extract a filler from one bundled structure, insert it into another, extract again — all correct). The same operation set passes substrate-validation gates on four embedding models and is shown to be substrate-portable across three of them.
We present Clawling, a self-reproducing digital organism implemented in Rust that runs entirely on consumer hardware using local LLMs. Each instance carries a persistent identity — a set of text files compiled into the binary — and accumulates individualized knowledge through a session-by-session learning file (`memory.