FastContext: Why Coding Agents Waste Half Their Tokens on Repo Search
Microsoft's FastContext shows coding agents burn 56% of tool turns on exploration. A 4B subagent cuts token use 50% and lifts SWE-bench scores 3 points.
Coding-Agents
Google Jules Review: The Async Coding Agent Worth $20/Month?
Google Jules queues coding tasks, runs them in a cloud VM, and opens PRs while you sleep. Free tier gives 15 tasks/day. Here's what worked and what didn't.