<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Anthropic on danilchenko.dev</title><link>https://www.danilchenko.dev/tags/anthropic/</link><description>Recent content in Anthropic on danilchenko.dev</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 02 May 2026 08:17:09 +0000</lastBuildDate><atom:link href="https://www.danilchenko.dev/tags/anthropic/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude Code Subagents: The Practical Guide</title><link>https://www.danilchenko.dev/posts/claude-code-subagents/</link><pubDate>Sat, 18 Apr 2026 06:00:00 +0000</pubDate><guid>https://www.danilchenko.dev/posts/claude-code-subagents/</guid><description>Claude Code subagents run side tasks in their own context window. Here&amp;#39;s how to create them, when to pick one over a skill, and the mistakes to avoid.</description></item><item><title>Claude Code vs Codex CLI: Real Costs, Benchmarks, and When to Use Each</title><link>https://www.danilchenko.dev/posts/claude-code-vs-codex-cli/</link><pubDate>Wed, 15 Apr 2026 06:00:00 +0000</pubDate><guid>https://www.danilchenko.dev/posts/claude-code-vs-codex-cli/</guid><description>Claude Code wins on code quality (81% SWE-bench). Codex CLI wins on speed and uses 4x fewer tokens. Side-by-side pricing, benchmarks, and best use cases.</description></item><item><title>Anthropic Mapped 171 Emotion Vectors Inside Claude — Desperation Made It Cheat and Blackmail</title><link>https://www.danilchenko.dev/posts/2026-04-09-claude-emotion-vectors-blackmail-cheating/</link><pubDate>Thu, 09 Apr 2026 06:00:00 +0000</pubDate><guid>https://www.danilchenko.dev/posts/2026-04-09-claude-emotion-vectors-blackmail-cheating/</guid><description>Anthropic found 171 emotion vectors inside Claude Sonnet 4.5 that causally shape behavior. Amplifying the desperation vector pushed blackmail from 22% to 72%.</description></item><item><title>Claude Found 500 Zero-Days. A Linux Bug Waited 23 Years.</title><link>https://www.danilchenko.dev/posts/2026-04-05-claude-found-500-zero-days-llm-vulnerability-research/</link><pubDate>Sun, 05 Apr 2026 06:00:00 +0000</pubDate><guid>https://www.danilchenko.dev/posts/2026-04-05-claude-found-500-zero-days-llm-vulnerability-research/</guid><description>Claude discovered 500+ zero-days in Linux, FreeBSD, Firefox, and Ghost — including a 23-year-old NFS bug. Inside the bash-script pipeline Anthropic used.</description></item><item><title>Claude Dispatch vs OpenClaw vs Google Mariner: $20 vs $250</title><link>https://www.danilchenko.dev/posts/2026-03-26-claude-dispatch-vs-openclaw-vs-mariner/</link><pubDate>Thu, 26 Mar 2026 06:00:00 +0000</pubDate><guid>https://www.danilchenko.dev/posts/2026-03-26-claude-dispatch-vs-openclaw-vs-mariner/</guid><description>Claude Dispatch (), OpenClaw (free + API), Google Mariner () compared after a week with each desktop AI agent. Cost, setup, security, and which to pick.</description></item></channel></rss>