Can AI classifiers follow meaning when the words disappear?
I built a numeric semantic transport for AI agents, then used Decoder and Doer failures to test what survives when ordinary language is removed from the wire.
Topic
AI 5
5 notes filed under AI.
Recommendation is not publication authority
Lessons from an X publishing experiment in keeping research, draft recommendations, approval, and measurement separate.
Why naive RAG fails for coding agents—and what Satori does instead
Why fixed text chunks are weak evidence for code changes, and how Satori combines symbol-aware chunking, hybrid retrieval, freshness checks, and exact bounded reads.
Why AI cleanup should not be the extraction engine
How PromptReady changed AI cleanup from raw HTML rewriting into a quality-gated pass over a local Markdown baseline.
Why semantic code search is not enough for coding agents
Notes on building Satori around deterministic MCP workflows, exact reads, stale-index warnings, and bounded retrieval contracts.