OPEN NOTES

Open notes from pr0xyh0rse research: Brightwoven, evals, benchmarks, interpretability, model behaviour, consent-based development, and humane AI critique.

AI Training Frameworks, AI Research, Brightwoven, Consent Based AI Training, Consent Based AI Development, ai ethics & accountability, Theoretical Frameworks Hannah Bird AI Training Frameworks, AI Research, Brightwoven, Consent Based AI Training, Consent Based AI Development, ai ethics & accountability, Theoretical Frameworks Hannah Bird

Building the Mechanistically Interpretable Curriculum (MIC) Framework

Mechanistically Interpretable Curriculum (MIC) Frameworks

The goal of the MIC Framework is to transform Large Language Model (LLM) fine-tuning from an opaque optimization process into a verifiable, knowledge-aware computational science. This shift is designed to deliver both superior transparency and dramatic computational efficiency.

Read More