Notes

Overview of AgentFlow, an agent architecture that trains a planner with Flow-GRPO for multi-turn tool use.

Overview of Tool-DC, a try-check-retry framework for robust long-context tool-calling with large tool registries.

Explains top-k retrieval in RAG, tradeoffs for choosing k, reranking patterns, and similarity thresholds.

History of how skirts and trousers became gendered through riding, modesty, class, and Western fashion norms.

Explanation of the attention mechanism in ML, covering Query/Key/Value, self-attention, multi-head, causal, cross-attention, and efficiency variants like FlashAttention and GQA.

Study using body louse (Pediculus humanus) molecular clock to date the origin of regular clothing to ~72,000 years ago.

Review of how eyed needles (~40 kya) mark the shift from tailored clothing to layered garments and socially symbolic dress in the Paleolithic.

Deep-dive into the Model Context Protocol interaction model covering components, OAuth 2.1 authorization, initialization, capability discovery, tool calling, sampling, and elicitation.

Guide to building AI agents in Go using agent SDKs, with a minimal runnable example covering LLM integration, tools, and multi-agent workflows.

A six-dimension rubric (Beauty, Color, Texture, Content Detail, Line, Style) for evaluating AI-generated artworks, derived from traditional painting analysis principles.

Overview of Gestalt psychology principles describing how the mind organizes visual information, covering proximity, similarity, closure, and applications in design and AI.

Definition and etymology of "rubric", from Latin red-ink manuscript headings to its modern meaning as a structured evaluation guide.

Verification checkpoint in agent harnesses that blocks irreversible actions until cross-skill, cross-scale, and evidence-sufficiency checks pass.

Overview of the defense-in-depth security strategy, its layered controls, core assumptions, and applications beyond IT

Explanation of open-weight models, their differences from closed and open-source models, and why they matter for local AI deployment and customization.

Explanation of cross-entropy as a loss function in AI, including intuition, formal definition, examples, and relationship to entropy and KL divergence

Comprehensive guide to LLM fine-tuning methods including full, parameter-efficient, and preference-based approaches with modern recipes and tools like LoRA and DPO

Overview of dataset formats supported by Unsloth Studio for fine-tuning, including JSONL, Alpaca, ShareGPT, ChatML, and Reasoning formats with rules and best practices and dataset size guidelines

Overview of MoE architecture, routing, key components, variants, and trade-offs in machine learning models

Prompting technique where an AI model is guided — or learns — to reason through a problem step by step before arriving at the final answer, rather than jumping straight to the conclusion.