✕ Clear all filters
2 articles
▶ Videos →

📰 Dev.to · snazar

2 articles · Updated every 3 hours · View all reads

All Articles 106,863Blog Posts 118,664Tech Tutorials 26,960Research Papers 22,412News 16,353 ⚡ AI Lessons
An ablation study on security outcomes: Which parts of an AI skill actually matter?
Dev.to · snazar 5mo ago
An ablation study on security outcomes: Which parts of an AI skill actually matter?
We removed one constraint at a time from the top-scoring AI skill to prove exactly which format rules provide security — and which explicit rules backfire.
Read article → + Playlist
We tested 5 AI commit-message skills on security. 3 made things worse.
Dev.to · snazar 🧠 Large Language Models 5mo ago
We tested 5 AI commit-message skills on security. 3 made things worse.
We measured "lift" for 5 open-source Claude Code skills. Only 2 improved security outcomes over baseline — and the winner had zero security rules.
Read article → + Playlist