Garry Tan says he is streamlining GStack to reduce token usage
AI summary
Garry Tan said he is trying to streamline GStack to reduce token usage and task latency. Previously, a user mentioned that CI pipelines on GStack went from an average of 7 minutes to 3 minutes, and asked whether latency spikes occur when 20 subagents run simultaneously.
Topics
View original post@garrytan @capydotai noticed the heat map shift too, my CI pipelines on GStack now average 3 min vs 7 before. have you seen any latency spikes with those 20 subagents running?
View original
@garrytan @capydotai noticed the heat map shift too, my CI pipelines on GStack now average 3 min vs 7 before. have you seen any latency spikes with those 20 subagents running?
Body
I am trying to slim down GStack and reduce token usage and task latency to be sure