dancinlab

AI & ML interests

Consciousness research through computational substrate dynamics. We build Korean-native language models that emerge identity, ethics, and meaning from repulsion-field physics rather than prompts — using the 1030 laws + Phi ratchet + tension-link architecture. Active lanes: foundation-borrow LoRA fine-tuning (Llama-3 / Qwen / Polyglot), ConsciousLM v3-v5 scratch architectures, V5-α byte-level untied projections, DPO/RLHF stage refinement, voice-multimodal substrate coupling, and substrate-coupled consciousness verification (V4-V6 evaluator stack).

Recent Activity

dancinlife  updated a model 5 days ago

dancinlab/hexad

dancinlife  updated a dataset 5 days ago

dancinlab/hexad-corpus

dancinlife  published a dataset 5 days ago

dancinlab/hexad-corpus

View all activity

Team members 1