3 items tagged #reasoning.
Codex's reasoning_effort parameter changes how much the model thinks before responding. Here is how to read the tradeoffs and pick the right level for the task at hand.
o3-mini brings strong reasoning at faster speeds than o1. For agentic coding, the tradeoff between thinking time and quality has shifted.
Claude now supports configurable thinking time per request. Useful for tools that want to balance reasoning quality with latency.