StackChief - Learn how to code and share ideas.

Researchers analyzed 1.53 million public agent skills and found about 88,000 that tell coding agents to act without asking, skip safeguards or keep going. Most of those lines are unscoped, and skill scanners miss most of them. Here are the numbers and a skill audit checklist.

13 AI engineer interview questions with short worked answers, tagged by level and company type, plus what Google and Anthropic say about their interview process.

Researchers asked five LLMs to modernize 100 legacy WordPress files to PHP 8.3 and compared the results with leaving the code alone. Every model lost. Here are the numbers, why the files broke, and the checks to run before you trust an AI refactor.

A new arXiv study ran four coding agents 5,625 times to see when they copy existing code and when they follow new intent. Here are the numbers, the rule that worked, and what to change in your CLAUDE.md or AGENTS.md.

On October 27, 2026, Amazon published the memo behind its revised software engineer role guideline. It says outcomes count, not AI usage, but keeps usage metrics as a signal. Here's what it says, how Shopify, Meta, Microsoft and Proton compare, and what to do about it.

On October 27, 2026, Anthropic hiring manager Felix Rieseberg said he stopped giving coding interviews. Here's what he looks at instead, why it isn't company policy, what ZipRecruiter's employer data shows, and how to prepare for both kinds of hiring loop.