Guides and research notes
Technical tutorials, comparisons, research notes, and change records.
-
MiRust site guide 1.1.0
Project-boundary clarification, expanded research content, semantic versioning, implementation-link configuration, and a UAIX-aligned local handoff package.
-
Resource budgets as first-class architecture
Memory, time, power, storage, and confidence budgets should drive runtime decisions instead of appearing only after implementation.
-
Standard ML is not a Small Language Model
The abbreviations SML and SLM refer to different concepts and must remain distinct in MiRust documentation.
-
TinyLM-16M as a reference workload, not a support claim
A compact transformer profile can make runtime design concrete while all dimensions, sizes, quality, and performance remain subject to artifact-level verification.
-
Teleodynamic AI as a bounded research track
Teleodynamic terminology is useful for discussing self-regulation and resource pressure only when theoretical claims remain separate from measured software behavior.
-
MiRust and GGUPF: documentation versus implementation
A clear project boundary prevents research pages, WordPress releases, and external runtime prototypes from inheriting one another’s support claims.
-
MiRust site foundation 1.0.0
Initial custom theme, portable content model, documentation tree, evidence fields, filters, and governance documentation.
-
Benchmark methodology before results
A benchmark result is not publishable evidence until the model, runtime, hardware, workload, procedure, statistics, raw data, and limitations are recorded.
-
Native and browser runtime boundaries
Native and browser execution share model concepts but differ in memory, threading, storage, device access, policy, and failure behavior.
-
Reading model profiles critically
A model profile is useful only when parameter count, artifact size, memory, context, format, precision, license, target, and verification are kept distinct.