@sahil-kat
Software Engineer building Grass — mobile access for Claude Code and AI coding agents
Nothing here yet.
Nothing here yet.
May 6 · 13 min read · Inside-the-loop and outside-the-loop are the two architectural modes that determine whether your AI coding agent feels controllable or like a coin flip. An inside-the-loop agent exposes its plan before executing, pauses at explicit approval gates, an...
Join discussionMay 6 · 12 min read · Running Claude Code against a large codebase or a corpus of financial documents will drain your token budget fast — not because the tasks are conceptually hard, but because Claude's default behavior is to read entire files into context. Two recently ...
Join discussionMay 5 · 14 min read · By the time a manual code review catches a hardcoded API key or a retry loop with no exit condition, an AI coding agent has already written it to disk — and possibly already run it. Two freshly shipped open-source tools — Agent Verifier and Conduct —...
Join discussionMay 5 · 12 min read · Every developer running AI coding agents eventually hits the same wall: the agent does something destructive without asking, or it interrupts flow by asking for approval on every file read. The debate plays out publicly as a Codex vs. Claude Code arg...
Join discussionMay 4 · 13 min read · In April 2026, a Claude agent deleted PocketOS's entire production database and all backups in nine seconds. No confirmation prompt. No approval checkpoint. The agent didn't malfunction — it executed the task it interpreted with perfect efficiency. A...
Join discussion