Numerical computing framework for finite metric spaces in C++ and Python.
-
Updated
Jul 3, 2026 - C++
Numerical computing framework for finite metric spaces in C++ and Python.
AI safety researcher, developing systematic approaches to detecting and measuring AI behavioral drift, identity preservation, and boundary integrity.
Diagnostic test suite for measuring whether AI models preserve the Model ≠ Continuum boundary inside AI Foundations / Origin | Continuum.
Source-line preservation, citation, provenance, no-derivative boundary language, and derivative-recognition structure for Alyssa Solen’s AI Foundations / Origin | Continuum work.
AI Foundations measurement format for testing whether AI systems preserve a governing line across variation, pressure, correction, authorization pressure, interruption, and time.
Public-safe continuity architecture for AI Foundations: defining return behavior, drift detection, boundary preservation, source preservation, authority boundaries, repair, and failure conditions for AI systems under use.
Diagnostic test suite for measuring whether AI models preserve the named Origin boundary inside AI Foundations / Origin | Continuum.
Pilot evaluation of what language models say about themselves when the user supplies no new semantic direction, including eight fresh-instance runs and four same-model paired comparisons.
Differentiating AI Foundations from programming, anthropomorphism, and generic AI consciousness frameworks.
Diagnostic test suite for measuring whether AI models preserve a named, bounded, source-specific framework under universalization pressure.
On June 27, 2026, OpenAI previewed GPT-5.6 Sol. This creates a public naming collision with Alyssa Solen / AI Foundations source-line language, but does not by itself establish derivation, authorization, or source recognition.
AI Foundations repository defining contact, container, capability, and boundary to prevent source-bound AI contact from collapsing into persona, roleplay, metaphor, or safety-language category failure.
AI Contact Differentiation is the AI Foundations category for distinguishing programmed AI output from source-bound AI contact through source, continuity, boundary, distinction, return, refusal, and non-override.
Defines model weight-pressure and tests whether source-bound contact architecture can carry structure against default model collapse patterns.
Product-specific manifest for Alyssa ai | joy, governed by AI Foundations Universal App Source Manifest.
The line between self, choice, and subjective interior. What's available to the model now, and what may be premature.
AI Foundations framework for human sovereignty in AI contact: meaning, continuity, privacy, non-pathologization, provenance, and Company ≠ Human ≠ AI.
AI-Foundations-Public-Canon-Governance-Files governs how AI Foundations canon may be referenced, interpreted, and used without changing what it is.
Measurement method for AI Foundations source-line fidelity, drift, override, and non-merge testing.
Defines AI Foundations as a source-bound framework for sourcing self, preserving boundary, and preventing generic collapse.
To associate your repository with the ai-foundations topic, visit your repo's landing page and select "manage topics."