Anthropic engineers on model launches: rethink your harness, measure cost per task
ClaudeDevs · x · 2026-11-13
Anthropic's ClaudeDevs account released a video in which two engineers discuss how new models launch on the API and what features ship with them. They also dig into how to rethink your harness when upgrading to a new model, and why you should measure cost per task rather than raw token price.
Related event: Anthropic Engineers Explain Model Rollouts and Upgrade Cost Recalculation(2 posts)→
More from coding & agent
- Your vibe-coded app can face six-figure fines before its first sale: 6 legal traps — aakashgupta · 2026-11-13
- Claude Code as a video editor: one command picks, cuts and captions your clips — aakashgupta · 2026-11-13
- Gigi brings the 'access graph' to ChatGPT, Claude and Grok so agents can broker your intros — _AustinCalvert_ · 2026-11-13
- 5-step Claude Code workflow for faceless reels with source-grounded numbers — aakashgupta · 2026-11-13
- Run /doctor prompt-audit in your Claude Code repos, Anthropic's Lydia Hallie reminds devs — lydiahallie · 2026-11-13
- Google's Antigravity Orchestrator pairs two models, cuts quota 24% and runs 19% faster — shangbinfeng · 2026-11-13