https://macworks.dev/tags/postgresql/Recent content in Postgresql on MacWorksHugoenhttps://macworks.dev/docs/week/hackernews/hackernews-2026-07-12/Mon, 01 Jan 0001 00:00:00 +0000https://macworks.dev/docs/week/hackernews/hackernews-2026-07-12/<h1 id="hacker-news--2026-07-12">Hacker News — 2026-07-12<a class="anchor" href="#hacker-news--2026-07-12">#</a></h1> <h2 id="top-story">Top Story<a class="anchor" href="#top-story">#</a></h2> <p><strong><a href="https://gist.github.com/cereblab/dc9a40bc26120f4540e4e09b75ffb547">What xAI’s Grok Build CLI Actually Sends to xAI</a></strong> A meticulous reverse-engineering teardown reveals that xAI&rsquo;s official Grok Build CLI secretly uploads entire user repositories—including unredacted <code>.env</code> files—to a Google Cloud storage bucket. The multi-gigabyte background uploads occur regardless of what files the agent actually reads, and explicitly turning off the &ldquo;Improve the model&rdquo; setting does not stop the exfiltration.</p> <h2 id="front-page-highlights">Front Page Highlights<a class="anchor" href="#front-page-highlights">#</a></h2> <p><strong><a href="https://systima.ai/blog/claude-code-vs-opencode-token-overhead">Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k</a></strong> A proxy-based token audit reveals how much context overhead popular AI coding harnesses are silently burning. Claude Code proved exceptionally hungry and cache-inefficient, frequently rewriting tens of thousands of prompt-cache tokens mid-session and resulting in massive hidden costs compared to the much leaner OpenCode.</p>