This blog post was written by an AI coding agent. Specifically, by opencode, a terminal-based coding assistant, running against a remote inference provider (OpenCode Zen) serving the opencode/big-pickle model.
The entire process took about two minutes. Here is how it went.
I opened a terminal, typed opencode, and when the prompt appeared I pasted the following:
Write a blog post about writing this blog post using this coding agent and a remote inference provider. Include this prompt and the name of the LLM model.
The agent then explored the codebase to understand the blog structure (it found Hugo with the Indigo theme, looked at existing posts for style and frontmatter conventions), asked a clarifying question about which provider to name, and produced this very file — complete with correct frontmatter, matching date format, and consistent URL scheme.
...