Skip to content

Blog Posts

Thoughts, experiences, and technical insights from my journey in software development.

Popular hashtags

Cover Image for Claude Code Only Reads AGENTS.md If Telemetry Is On

Claude Code Only Reads AGENTS.md If Telemetry Is On

Disabling telemetry in Claude Code silently blocks AGENTS.md from loading — no error, no warning. A developer reverse-engineered why.

#claude-code#anthropic#developer-tools#privacy#ai-coding-agent
Cover Image for Claude Opus 5.5 Launches: Stronger, 40% Cheaper

Claude Opus 5.5 Launches: Stronger, 40% Cheaper

Anthropic's Claude Opus 5.5 matches Fable 5.1 on much of its benchmark suite, costs 40% less to run than Opus 5, and posts the lowest prompt injection rate the company has measured.

#anthropic#claude#llm#ai-coding-agent#developer-tools
Cover Image for Real-SWE: The Benchmark That Exposes AI Coding Agents

Real-SWE: The Benchmark That Exposes AI Coding Agents

The top model solves just 38.8% of tasks pulled from real enterprise codebases. Real-SWE shows the gap between demo and production.

#ai-coding-agent#benchmark#swe-bench#claude-code#developer-tools