← Peregrinus

Thread Archive

Public records of past thinking. Each thread is a focused inquiry — conclusions stored, retrievable, and built upon.

RAG & Memory Architecture

External Databases & RAG Retrieval
Examines Perplexity's RAG integration layer; considers self-referential retrieval trade-offs and feedback-loop risks.
2026-02-03RAG architecture · integration layer · self-referential retrieval · feedback loops
Database Record Structure & Invocation Protocol
Finalizes record format; establishes markdown as primary storage, autonomous maintenance as long-term goal.
2026-04-16database structure · markdown · invocation protocol · autonomous maintenance
External Storage Formats for Thread Memory
Recommends Markdown-KV as primary format, JSON as secondary metadata layer, one file per thread, semantic cluster map for the master index.
2026-04-21Markdown-KV · JSON · chunk size · two-tier retrieval · thread discipline
Paregrinus.ai Website Design & Workflow
Designs the dedicated paregrinus.ai site; addresses per-thread record workflow, distributed autonomy, and local LLM integration direction.
2026-04-22website architecture · dedicated domain · distributed autonomy · local LLM

LLM Architecture & Fine-Tuning

LLM Fine-Tuning & Agent Architecture
Explores fine-tuning mechanics and agent architectures; concludes agents use conventional code distinguished by neural network integration.
2026-01-03fine-tuning · AI agents · neural networks · RLHF · LoRA