- OpenAI Codex Agentic Coding
OpenAI's new Codex runs coding tasks in cloud sandboxes, async and in parallel. Here's what that means for ML engineers.
5 min - Agentic Workflows Need State And Guardrails
Why useful LLM agents depend on tools, state machines, evals, and careful failure handling.
7 min - Structured Outputs Made LLMs Easier To Ship
Why schemas, tool calls, and constrained decoding changed how production LLM apps are built.
6 min