<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>vtriv blog</title><description>Writing on durable context for LLMs — what&apos;s worth keeping, how assistants use a context layer, and what we&apos;re building at vtriv.</description><link>https://vtriv.com/</link><item><title>The cost of starting over</title><link>https://vtriv.com/blog/starting-over/</link><guid isPermaLink="true">https://vtriv.com/blog/starting-over/</guid><description>Every new chat begins from zero. A calmer way to work with assistants that don&apos;t remember.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item><item><title>What&apos;s worth keeping for your AI</title><link>https://vtriv.com/blog/what-to-keep/</link><guid isPermaLink="true">https://vtriv.com/blog/what-to-keep/</guid><description>Once your assistant can read a context layer, the question is what to put in it. Four kinds that earn their place.</description><pubDate>Tue, 09 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>