We did two separate studies, one of accuracy and cost the other of accuracy and latency. Most of our studies used cost as the definition is pretty clear and less sensitive to environmental conditions (e.g. LLM provider…
I am on the team. Here are some responses to your questions: >Could I ignore all flow runs that have an estimated cost above a certain threshold, so that the overall cost of optimization is less? Suppose I choose an…
We did two separate studies, one of accuracy and cost the other of accuracy and latency. Most of our studies used cost as the definition is pretty clear and less sensitive to environmental conditions (e.g. LLM provider…
I am on the team. Here are some responses to your questions: >Could I ignore all flow runs that have an estimated cost above a certain threshold, so that the overall cost of optimization is less? Suppose I choose an…