"Better" is doing a lot of work when someone says LLMs write better code than humans. This post breaks it into four different things you could be measuring. 🧵
{ author: @dannwaneri }
New author alert! 🎉
@PaulSuvran27548 ran a fresh-clone checker on the repos of the top 100 npm packages, found 9 of its 10 build-failing findings were false, and fixed the tool until every remaining one was real. It's their first DEV post.
New author alert! 🎉
@nasersadrmanesh walks through four open-source tools for AI in online stores, including a WooCommerce MCP server where every write is previewed first and applied only on confirmation. It's their first DEV post.
A human approved the order, and the agent answered "Tool order_part not found". A Dart agent, an MCP tool and one missing lookup on restart. 🧵
{ author: @esratech + @GoogleDevExpert }
