<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Web Security on MacWorks</title><link>https://macworks.dev/tags/web-security/</link><description>Recent content in Web Security on MacWorks</description><generator>Hugo</generator><language>en</language><atom:link href="https://macworks.dev/tags/web-security/index.xml" rel="self" type="application/rss+xml"/><item><title>2026-06-21</title><link>https://macworks.dev/docs/archives/hackernews/hackernews-2026-06-21/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://macworks.dev/docs/archives/hackernews/hackernews-2026-06-21/</guid><description>&lt;h1 id="hacker-news--2026-06-21"&gt;Hacker News — 2026-06-21&lt;a class="anchor" href="#hacker-news--2026-06-21"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;h2 id="top-story"&gt;Top Story&lt;a class="anchor" href="#top-story"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;The most significant development today isn&amp;rsquo;t a new software framework, but Anthropic&amp;rsquo;s quiet leap into hardware control with &amp;ldquo;Project Fetch: Phase Two&amp;rdquo;. Claude Opus 4.7 can now autonomously write code to control a robotic quadruped, completing complex physical tasks 20 times faster than human engineering teams. This signals a massive shift toward physical agentic AI, where models transition from merely assisting humans in a terminal to directly operating off-the-shelf hardware through public interfaces.&lt;/p&gt;</description></item><item><title>Hacker News</title><link>https://macworks.dev/docs/week/hackernews/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://macworks.dev/docs/week/hackernews/</guid><description>&lt;h1 id="hacker-news--week-of-2026-06-20-to-2026-06-26"&gt;Hacker News — Week of 2026-06-20 to 2026-06-26&lt;a class="anchor" href="#hacker-news--week-of-2026-06-20-to-2026-06-26"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;h2 id="story-of-the-week"&gt;Story of the Week&lt;a class="anchor" href="#story-of-the-week"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;This week, the unchecked firehose of AI-generated code finally forced structural changes across the ecosystem, culminating in GitHub introducing persistent PR limits after projects like OpenClaw were crushed by thousands of low-effort &amp;ldquo;slop&amp;rdquo; PRs. This friction bled directly into open-source philosophy, most notably when the GNU project outright rejected a highly performant Metal/OpenGL Emacs GPU backend simply because the author used LLMs. The era of purely human-driven open-source maintenance is effectively over, forcing maintainers to rely on automated governance just to survive the noise.&lt;/p&gt;</description></item></channel></rss>