The New StackGitHub
This week’s news from Zed, Anthropic, and OpenRouter shows why better harnesses matter more than better models

Our five most-read stories this week covered code collaboration, a model router, a UI change, a benchmark, and a caching tutorial.
Read at The New Stack ↗More from The New Stack on Accept All

GitHubClaude couldn’t hack OpenAI. Then Anthropic shipped Opus 5. The New Stack

GitHubKubernetes can run AI inference. But can it count the real cost? The New Stack

GitHubYour agent is only as good as your infrastructure The New Stack

GitHubOpen-weight models now handle a majority of tokens on Vercel’s AI Gateway. But Anthropic still takes 64% of the spend. The New Stack

GitHubCode review is burning out your best engineers The New Stack
