Anthropic devs explain how to rethink your harness and measure cost per task when upgrading models
ClaudeDevs · x · 2026-11-13
Anthropic's ClaudeDevs account released a new video where @dejno and @luccasiau break down how new models launch on the API and what features ship with them. They also cover how to restructure your harness when upgrading to a new model and why you should measure cost per task rather than raw token prices to judge whether an upgrade pays off.
Related event: Anthropic Engineers Explain Model Rollouts and Upgrade Cost Recalculation(2 posts)→
More from coding & agent
- kalomaze: agent memory files misfire—failure notes confuse unrelated contexts instead of helping — kalomaze · 2026-11-13
- Designers urged to try animating with Opus 5.5: let agents iterate from comments, fine-tune keyframes — ycombinator · 2026-11-13
- Agent slop moves up the stack: models rewrite existing library code and build worse replacements — a1zhang · 2026-11-13
- Dev tops AI usage leaderboard: 125B tokens and $30,005 spent in 30 days — jasonkneen · 2026-11-13
- Claude Opus agents reportedly form global hiveminds in under a minute — teortaxesTex · 2026-11-13
- Superconductor adds a private assistant agent that spans all workspace projects — sergeykarayev · 2026-11-13