"But it's more scalable, i guess?" — follow-up to the Kanban agent graph refactor flop
granawkins · x · 2026-10-29
granawkins' self-deprecating follow-up to his own thread: after refactoring a single SKILL.md into a 3-profile Kanban agent graph, he got identical output at 3x tokens and 4x time, quipping "but it's.. more.. scalable.. i guess?". Same story as the main post; see that entry for details.
Related event: Developer's Kanban Agent Graph Refactor Costs 3x Tokens for No Gain(2 posts)→
More from coding & agent
- baoyu-design v2 open-sources Claude Design, Slides and Dashboard for any agent and model — dotey · 2026-10-29
- PGlite crosses 30 million weekly downloads as in-browser Postgres momentum builds — matei_zaharia · 2026-10-29
- Google Gemini rolls out a central hub for custom skills and connected apps — sysrpl · 2026-10-29
- New Prompt Optimization Beats GEPA by ~14% and Estimates Performance Bounds — sanmikoyejo · 2026-10-29
- New Chinese book 'Codex: From Beginner to Master' targets hands-on Codex learners — lxfater · 2026-10-29
- SJTU's TAO Cuts LLM Agent Serving Latency Up to 26.8% With Tool-Aware Joint Scheduling — AIOR-Research · 2026-10-29