OpenAI still leads in agentic terminal coding, but by less.
Claude can plan the work and then run hundreds of parallel subagents in a single session (and with Opus 4.8, the agents can run for even longer)
That’s one way to turn profitable before the IPO, I guess. Goodbye tokens.
I really should start charging my employer per individual thought, regardless of the quality of accuracy of said thought. I’m sure I’d be onto a winner with that one.