The HTTP QUERY method (RFC 10008) implemented in Python — how it differs from GET and POST
Implementing RFC 10008 HTTP QUERY in Python with Starlette: safe, idempotent, cacheable requests with a structured body, and how it complements GraphQL.
All posts
Deterministic AI agent tests with AIMock — mocking LLMs, vector DBs, MCP, and A2A on one port
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.
Five rounds to a blog logo with an AI agent — the /logo skill and three scripts they left behind
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.
Autoregressive vs diffusion image generation — how gpt-image-1 and DALL-E 3 differ
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.
A 2 MB PNG became 316 KB WebP — but only before the first commit
Measuring PNG, JPEG and WebP for article figures, why re-compressing the PNG made it larger, and why converting an image git already tracks reclaims nothing.
My work email was in all 27 personal repos — fixing it with git includeIf and filter-repo --mailmap
Git identity belongs to the directory, not the repo. includeIf gitdir fixes it going forward; git filter-repo --mailmap fixes the commits already pushed.
Astro content collections instead of a CMS — MDX over Markdown, and where the foreign keys went
Why this trilingual Astro blog has no CMS: the directory layout images forced, MDX over Markdown, and a tag registry standing in for foreign keys.
A2A vs MCP — why agent-to-agent needs its own protocol, and why both chose HTTP over gRPC
Why MCP alone is not enough for agent-to-agent communication: peer equality, Agent Card discovery, async task state, and why both protocols chose HTTP.
Python's yield streams input into a running AI agent — the difference from return, in Node.js too
How Python's yield differs from return, and how an async generator passed as a prompt streams input into a long-running AI agent, with the Node.js equivalent.