Subscribe to Darius AI Weekly
Around 8 a.m. Beijing time every Monday, I pick the 6 AI stories from the past seven days of my daily brief that matter most to people building products, and send them to your inbox.
Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link.
What you'll get
- 6 stories, each with its primary source. On the site you get the key points and my take.
- 2 open-source picks from trending AI projects on GitHub, with why they made the cut.
- One email a week. No ads. One-click unsubscribe in every email.
How it works
- Enter your email and submit
- Within half an hour, click "Confirm subscription" in the email we send
- Your first weekly arrives the following Monday
The latest issue
This week the risk moved from model quality to the plumbing around it: API versions, gateways and dependencies
- Claude API ships 2026-10-21, its first new version since 2023-06-01: temperature, top_p and top_k now return errors, and new major SDKs move to Apache 2.0
- LiteLLM 1.107.0 was a poisoned release: malicious code ran through Python startup hooks and stole credentials without LiteLLM ever being imported
- Anthropic donates the Agent Skills standard to the Linux Foundation's AAIF: more than 70 agent platforms, about 1 million skills published and nearly 280 million installs
- OpenAI adds 12-hour prompt caching to the API, with writes at 2.5x the input price
- GitHub package firewall enters public preview, screening npm traffic between coding agents, CI and the registry
- OpenAI's frontier models and Codex workflows are coming to Google Cloud through Model Garden and Google Cloud Marketplace