<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Blog · Minh-Toan Ta</title><description>Articles on Claude, AI agents and the craft of software, explained with everyday life.</description><link>https://me.consonance.fyi/en/blog/</link><language>en</language><item><title>Grok Bot: what I would trust an always-on agent with</title><link>https://me.consonance.fyi/en/blog/grok-bot/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/grok-bot/</guid><description>Grok Bot, seen by an engineer who builds systems that must not be wrong: how xAI&apos;s agents work, what real marketplace Bots do, and my rules before I let one in.</description><pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate><category>grok-bot</category><category>agents</category><category>xai</category><category>trust</category><category>automation</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item><item><title>OSS Scanner: a free security inspection for critical open source</title><link>https://me.consonance.fyi/en/blog/anthropic-oss-scanner/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/anthropic-oss-scanner/</guid><description>Anthropic&apos;s OSS Scanner runs periodic AI security scans of critical open-source projects at no cost. What a report contains, who qualifies, how to enroll, and how to triage the results.</description><pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate><category>security</category><category>open-source</category><category>anthropic</category><category>ai</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item><item><title>pstack: Lauren Tan&apos;s rules for agents you can trust</title><link>https://me.consonance.fyi/en/blog/pstack-lauren-tan/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/pstack-lauren-tan/</guid><description>pstack, the skill plugin by Lauren Tan (@poteto) for Cursor and Grok Bot: trust one agent before running ten, fix mistakes at the root, and treat verification as infrastructure, down to TLA+ models.</description><pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate><category>grok-bot</category><category>agents</category><category>verification</category><category>tla-plus</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item><item><title>Claude Code in the cloud: one machine per task</title><link>https://me.consonance.fyi/en/blog/claude-code-in-the-cloud/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/claude-code-in-the-cloud/</guid><description>A cloud session gives each task its own machine and branch: several jobs run side by side, survive a sleeping laptop, and come back as pull requests.</description><pubDate>Wed, 07 Oct 2026 00:00:00 GMT</pubDate><category>claude-code</category><category>cloud</category><category>git</category><category>workflow</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item><item><title>Evaluating and improving an AI app, explained with an exam</title><link>https://me.consonance.fyi/en/blog/automating-eval-design-and-hillclimbing/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/automating-eval-design-and-hillclimbing/</guid><description>build-eval writes an exam for your AI app with you; hillclimb revises against it one change at a time, with held-out cases to catch cramming.</description><pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate><category>claude</category><category>claude-code</category><category>evals</category><category>llm</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item><item><title>Moving to Claude Sonnet 5.5: the three things that break</title><link>https://me.consonance.fyi/en/blog/building-with-claude-sonnet-5-5/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/building-with-claude-sonnet-5-5/</guid><description>Sonnet 5.5 is 30% faster than Sonnet 5 at the same per-token price. Swapping the model name is easy; three habits in your code are not.</description><pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate><category>claude</category><category>api</category><category>migration</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item><item><title>Claude Code mods: a small file that rewrites what you see</title><link>https://me.consonance.fyi/en/blog/getting-started-with-claude-code-mods/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/getting-started-with-claude-code-mods/</guid><description>What a Claude Code mod is, how it slots into the session as a hook, two examples from the official guide, and Recording Mode to hide secrets on screen.</description><pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate><category>claude-code</category><category>mods</category><category>plugins</category><category>privacy</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item><item><title>Claude Code&apos;s effort, explained: spending time, not intelligence</title><link>https://me.consonance.fyi/en/blog/spending-your-effort/</link><guid isPermaLink="true">https://me.consonance.fyi/en/blog/spending-your-effort/</guid><description>Effort doesn&apos;t make Claude smarter. It sets how much computing it spends, so how much it checks, tests edge cases and judges on its own.</description><pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate><category>claude-code</category><category>effort</category><category>workflow</category><author>tmtoan2601@gmail.com (Minh-Toan Ta)</author></item></channel></rss>