From token prediction: what temperature and top_p control, why hallucination is structural, prompt-leak attacks on the tokenizer, plus Extended Thinking.
From context to the finished LLM: the limits of RNNs, the birth of attention, the Transformer, GPT-3 scaling, RLHF alignment, and the era of efficiency.
The LLM as a by-product of unrelated problems: Turing on computability, Shannon on information, the perceptron, backpropagation, GPUs, and Word2Vec.
Whether fine-tuning can replace RAG for knowledge base search: what fine-tuning actually learns, when pure IR or long context wins, and what each costs.
AIMock mocks the whole AI stack on one port (LLM, vector DB, MCP, A2A), so an agent test suite runs in under three seconds with identical output every time.
Redesigning this blog's logo and code font with an AI agent: a broken SVG letterform, a regex bounding box, a wrong kanji, and the /logo skill it produced.
Why gpt-image-1 and DALL-E 3 differ: autoregressive tokens vs iterative denoising, the discrete-vs-continuous wall, DiT, and the three-way 2026 market.
Why MCP alone is not enough between agents: peer refusal, Agent Card discovery, task state, and why A2A v1.0 offers gRPC while MCP stays on HTTP.
