Agents Are Already Writing a Language You Can't Read
Compression toward machine-preferred notation isn't a future bet. It's already landing in context formats, agent protocols, and the files your harness reads.
We can't find the internet
Attempting to reconnect
Something went wrong!
Attempting to reconnect
Writing · Tag
36 posts on AI tools, page 2 of 3. Or browse the full writing index →
Compression toward machine-preferred notation isn't a future bet. It's already landing in context formats, agent protocols, and the files your harness reads.
Four Elixir options for schema-validated LLM output, scored on maintenance, provider coverage, retry behavior, and escape hatches.
José Valim's case for Elixir as a coding-agent harness holds up on the runtime. The tax is the ecosystem around it: sandboxing, plugins, and SDKs.
A restructure log: what broke in the AIOS v1 tree at multi-scope scale, why identity-first beats type-first, and what shipped in v2.
Model names scattered across every repo's config rot the day a model gets deprecated or repriced. One git-versioned markdown table fixes it for good.
Four Claude Code hooks I run, plus a decoder for hook errors: Stop hook error: JSON validation failed, denied by PreToolUse hook, No such file or directory.
Where TDD with Claude Code actually holds up in an Elixir/Phoenix codebase (ExUnit async, mix precommit, Ecto.Multi idempotency) and where it breaks.
The CLAUDE.md entries that actually earned their place on a real project: mistake-driven rules, not a speculative template you copy once and forget.
My team's $200 AI coding seats consume $1,800–$3,500 of API-priced tokens a month. The 10–17x arbitrage nobody prices in, and how to budget for it.
I open-sourced the AI operating system I run daily: a git-versioned markdown vault, cross-repo wiring, and a nightly ingest loop. Fifteen minutes to set up.
Your accumulated agent memory is a bet on one vendor's format. Build a portable, git-versioned knowledge layer any agent can read instead.
The Claude Code plugins that earn a permanent slot in my stack, sorted by what they actually change: my process, my domain expertise, or just friction.