<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>discostew test on Cloudflare</title><description>Local AI experiments and notes from testing what is possible now.</description><link>https://discostew.dev/</link><item><title>Good News: Jesus Is Risen</title><link>https://discostew.dev/posts/good-news-jesus-is-risen/</link><guid isPermaLink="true">https://discostew.dev/posts/good-news-jesus-is-risen/</guid><description>Just trying to share the Word: the tomb is empty, hope is alive, and Christ has conquered death.</description><pubDate>Mon, 06 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The fireworks test was really a runtime test</title><link>https://discostew.dev/posts/local-model-fireworks-approval-results/</link><guid isPermaLink="true">https://discostew.dev/posts/local-model-fireworks-approval-results/</guid><description>A receipt-heavy proof run for three local runtime lanes: GLM 5.2, MiniMax M3, and DeepSeek V4 Flash.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Proof: David Wilderness Stealth Prototype</title><link>https://discostew.dev/posts/proof-david-wilderness-stealth-prototype/</link><guid isPermaLink="true">https://discostew.dev/posts/proof-david-wilderness-stealth-prototype/</guid><description>Evidence from a real Godot 4 render and validation run for a hex-grid stealth tactics prototype about David reaching the Cave of Adullam.</description><pubDate>Wed, 17 Jun 2026 00:00:00 GMT</pubDate></item><item><title>ChromaDB was extra state, not extra evidence</title><link>https://discostew.dev/posts/chromadb-was-extra-state-not-evidence/</link><guid isPermaLink="true">https://discostew.dev/posts/chromadb-was-extra-state-not-evidence/</guid><description>Why I removed ChromaDB from Baseball RAG after realizing it did not give me anything the model and database could not already do better.</description><pubDate>Sat, 13 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Making AI Reliability Accessible</title><link>https://discostew.dev/posts/ai-reliability-accessibility/</link><guid isPermaLink="true">https://discostew.dev/posts/ai-reliability-accessibility/</guid><description>A short note from discostew on treating AI reliability as an accessibility practice, not just an infrastructure concern.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Fidelity over backward compatibility</title><link>https://discostew.dev/posts/fidelity-over-backward-compatibility/</link><guid isPermaLink="true">https://discostew.dev/posts/fidelity-over-backward-compatibility/</guid><description>Why I accepted breaking API changes in Propontis when the old schema hid important evidence boundaries.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>I fixed an eval by hashing the contract, not the file</title><link>https://discostew.dev/posts/hashing-the-contract-not-the-file/</link><guid isPermaLink="true">https://discostew.dev/posts/hashing-the-contract-not-the-file/</guid><description>Why an evaluation baseline should track the public behavior users depend on instead of private implementation bytes.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Let the LLM write the bio. Make the database check the facts.</title><link>https://discostew.dev/posts/let-the-llm-write-make-the-database-check-facts/</link><guid isPermaLink="true">https://discostew.dev/posts/let-the-llm-write-make-the-database-check-facts/</guid><description>A design note on generated biographies, stat-claim extraction, and using structured data to keep prose honest.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>MCP servers have a context tax</title><link>https://discostew.dev/posts/mcp-servers-and-context-tax/</link><guid isPermaLink="true">https://discostew.dev/posts/mcp-servers-and-context-tax/</guid><description>Why I do not want persistent MCP servers in my default Hermes profile unless the recurring value is obvious.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>The model should explain the evidence, not become the evidence</title><link>https://discostew.dev/posts/model-should-explain-evidence-not-be-evidence/</link><guid isPermaLink="true">https://discostew.dev/posts/model-should-explain-evidence-not-be-evidence/</guid><description>A short decision story about source authority, provenance, and keeping generated prose out of the truth path.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Removing ChromaDB made my RAG system more reliable</title><link>https://discostew.dev/posts/removing-chromadb-made-rag-reliable/</link><guid isPermaLink="true">https://discostew.dev/posts/removing-chromadb-made-rag-reliable/</guid><description>Why I removed a vector database from my baseball RAG project and kept DuckDB as the source of truth for structured facts.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>