Huzaifa Tahir

Claude Code's real ceiling isn't a vague rate limit — it's the shared five-hour usage window that resets on a clock, not on your deadline.

I ship with Claude Code myself. Per Anthropic's own usage docs, paid plans get a session usage limit that resets every five hours (the period...

Codex CLI's edge: open-source harness + OS sandbox

I ship client code with Claude Code. When I evaluate Codex as a second seat, the interesting part isn't another model race — it's that the harness itself is open-source and the OS sandbox is explicit.

OpenAI publishes Codex as a...

Claude Code scores higher. Codex costs ~7× less per task

I ship my own code with Claude Code. The question I keep getting from other freelancers isn't "which model is smarter?" — it's "which agent seat burns less money for the same week of client work?"

Artificial Analysis's...

Urgent care antibiotics: AI decision support that drafts stewardship plans

In urgent care, the hard part of a viral URI visit often isn't the diagnosis — it's the antibiotic conversation when a patient expects a prescription. Here's how I'd solve it with AI: stewardship decision...