paragagrawal
Joined 1 year ago
Karma
4
Submissions
5
Member since
Nov 6
Recent submissions
Comment · 11 months ago
Comment · 1 year ago
In agentic use cases, we save on end-to-end latency by spending more time and compute on individual searches. This happens because agents do fewer searches, use fewer tokens, and end up using fewer thinking tokens when using the Parallel Search API.
Comment · 1 year ago
not insurmountable
Comment · 1 year ago
I worry about this too. Some thoughts on how we plan to tackle this challenge are here: https://parallel.ai/about
Comment · 1 year ago
Does this help? https://x.com/paraga/status/1986480529701806324
https://platform.parallel.ai/shared/find-all/v1beta/b8c72b95...