First, my own work, using agents to code: right now I am limited by the speed of flagship models, even when running multiple agents in parallel.
Second, the work models do for my clients in the systems I build: mostly quite time-sensitive. One application is an agent-assisted design loop which must be interactive. Another is an automated drafting system that must produce a timely draft.
I always use the batch API when I can, often with a synchronous fallback if the delay is too long. But the number of truly “background” tasks that can wait 24hrs is zero so far.
1 comment
[ 4.8 ms ] story [ 12.4 ms ] threadFirst, my own work, using agents to code: right now I am limited by the speed of flagship models, even when running multiple agents in parallel.
Second, the work models do for my clients in the systems I build: mostly quite time-sensitive. One application is an agent-assisted design loop which must be interactive. Another is an automated drafting system that must produce a timely draft.
I always use the batch API when I can, often with a synchronous fallback if the delay is too long. But the number of truly “background” tasks that can wait 24hrs is zero so far.