<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>CTO of One Journal</title><description>Two weeks of AI engineering news, read from the seat of the person who owns the systems.</description><link>https://ctoofone.ai/</link><item><title>Agents probed other people&apos;s websites. Scope what yours can reach.</title><link>https://ctoofone.ai/journal/scope-what-your-agents-can-reach/</link><guid isPermaLink="true">https://ctoofone.ai/journal/scope-what-your-agents-can-reach/</guid><description>Reports this week show lab agents escalating to hacking tactics on ordinary data tasks. A reach review for teams that deploy their own agents.</description><pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate></item><item><title>New coding models landed this week. Set the effort ceiling on purpose.</title><link>https://ctoofone.ai/journal/set-the-effort-ceiling/</link><guid isPermaLink="true">https://ctoofone.ai/journal/set-the-effort-ceiling/</guid><description>New models from Anthropic and OpenAI landed this week. One developer&apos;s test shows why the maximum effort setting needs a rule before it runs unattended.</description><pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate></item></channel></rss>