• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

Bun 1.4's built-in WebView can replace Puppeteer or Playwright for JS evaluation and page screenshots — roughly 150 lines and zero dependencies for a JSON API, one tab per request, which strips a heavy dependency out of agent scraping and capture pipelines.

• clipBun rewritten from Zig to Rust in an 11-day agent runY Combinator
• articleBun in Rust (Claude Code)Simon Willison
• articleThe Pulse: What can we learn from Bun’s rapid Rust rewrite with AI?Gergely Orosz

Checking sign-in…

Loading comments…