Miguel Alonso Jr.

I made a skill for Claude Code/Codex/etc. for selecting models based on Artificial Analysis reported benchmarks & costs I figure it'll be useful for letting models setup subagents well, based on the actual task at hand github.com/tkellogg/mod...

GitHub - tkellogg/model-selection: A skill for model selection github.com

AI Weekly's analysis →

• The skill queries Artificial Analysis' API so subagents can rank available models by benchmark scores and cost before picking one for a task.
• API calls are cached on a daily basis to stay under Artificial Analysis' free tier limit of 100 requests per day.
• Install is a git clone into ~/.claude/skills, with an optional symlink into ~/.codex/skills for people running two agents.

Read full analysis →

View on Bluesky →

ZCode, the official development environment for GLM-5.2 zcode.z.ai/en

ZCode - Simple, Fast, Vibe‑Ready | Official Harness for GLM-5.2 zcode.z.ai

AI Weekly's analysis →

• ZCode is pitched on Z.ai's site as the 'Official Harness for GLM-5.2,' now on version 3.2.2 across macOS, Windows and Linux (Beta).
• GLM Coding Plans start at $16.20/month for Lite, $64.80 for Pro at 5x Lite usage, and $144 for Max at 20x usage.
• The harness leans on long-running Goals, multi-agent collaboration, and remote bot control from WeChat, Feishu and Telegram.

Read full analysis →

View on Bluesky →

lanius: an agent harness built for the great AI scale-down frontier models are too expensive to use 100%, and all the good ways to use them 5% of the time involve a heck of a lot of moving parts to coordinate lanius has messaging at the core timkellogg.me/blog/2026/07...

Lanius: AI Agents Need an OS, Not a Bigger Brain timkellogg.me View on Bluesky →

What would be different if labor was free? Fundamentally thinking of robots as a replacement for humans is thinking too small itcanthink.substack.com/p/what-would...

What Would You Do if Labor Was Free? itcanthink.substack.com View on Bluesky →

Two tools I recently learned about for sandboxing agents without needing a full VM nono.sh agent-safehouse.dev

Secure, capability-based runtime for AI agents | nono nono.sh View on Bluesky →

Two tools I recently learned about for sandboxing agents without needing a full VM nono.sh agent-safehouse.dev

Agent Safehouse agent-safehouse.dev View on Bluesky →

"Engineers should own the outer loop. Build agents you can answer for" - My closing keynote for AI Engineer World's Fair is now up and free to check out. www.youtube.com/watch?v=n97B...

youtube.com View on Bluesky →