<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
<channel>
  <title>Karl Livesey · ai</title>
  <link>https://livesey.io/tags/ai/</link>
  <description>Posts filed under ai.</description>
  <item>
  <title>Why TurboQuant Actually Matters</title>
  <link>https://livesey.io/posts/why-turboquant-actually-matters/</link>
  <guid isPermaLink="false">urn:uuid:2c5dc556-4735-50ca-bbd3-f93ecbc53705</guid>
  <pubDate>Sun, 29 Mar 2026 12:00:00 GMT</pubDate>
  <description>TurboQuant is interesting because it attacks KV cache pressure and inference memory cost, which are often the real bottlenecks once a model has to serve long contexts in production.</description>
</item>
</channel>
</rss>