Two agents, compared honestly
Claude, from Anthropic, and Codex, from OpenAI, are two takes on the same idea: an assistant that lives in your project rather than in a browser tab.
Read →Habits
A short list of working habits, each with the failure it prevents.
A commit behind you turns “undo the last twenty minutes” from archaeology into one command.
Before sending: can you say in one sentence what would make this attempt a success? If not, it is still a topic.
Be sceptical of a test written in the same turn as the fix: it can be shaped to pass rather than to check.
Claude, from Anthropic, and Codex, from OpenAI, are two takes on the same idea: an assistant that lives in your project rather than in a browser tab.
Read →The review is the part that was never delegable. It is also the part that gets skipped first.
Read →