alt Hacker NewsThe practical limit is the latency and inference cost. A full planning and validation loop burns a lot of tokens, and waiting for that cycle breaks flow compared to just writing the code.
The practical limit is the latency and inference cost. A full planning and validation loop burns a lot of tokens, and waiting for that cycle breaks flow compared to just writing the code.
Only if your flow is writing the actual code.
If you flow state involves elaborating complimentary specifications in parallel, it's marvelous