<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>devtake.dev — Muse Code</title><description>Articles on devtake.dev covering Muse Code.</description><link>https://devtake.dev/</link><language>en-us</language><item><title>Meta scrapped its plan to run 60% smaller teams on AI agents after incidents rose 40%</title><link>https://devtake.dev/article/meta-ai-native-agents-disruptive/</link><guid isPermaLink="true">https://devtake.dev/article/meta-ai-native-agents-disruptive/</guid><description>Internal documents reviewed by Reuters show Meta explored 60% team cuts under Project OT, then dropped it once its own agents started taking disruptive actions.</description><pubDate>Tue, 01 Sep 2026 07:45:00 GMT</pubDate><category>ai</category><category>ai</category><category>meta</category><category>ai-agents</category><category>agents</category><category>automation</category><category>layoffs</category><category>big-tech</category><author>dieter-morelli</author></item><item><title>Meta&apos;s Muse Code: a terminal agent built for repos most devs never touch</title><link>https://devtake.dev/article/meta-muse-code-agent/</link><guid isPermaLink="true">https://devtake.dev/article/meta-muse-code-agent/</guid><description>Meta&apos;s Muse Code is in beta on macOS and Linux, priced at $1.25 per million input tokens. Meta&apos;s own benchmarks put it behind Claude Opus 5.</description><pubDate>Thu, 06 Aug 2026 13:55:00 GMT</pubDate><category>ai</category><category>ai-agents</category><category>agentic-coding</category><category>meta</category><category>ai-models</category><category>benchmarks</category><category>claude-code</category><category>codex</category><category>terminal</category><author>dieter-morelli</author></item></channel></rss>