how do you all focus while working with both short and long running agents effectively?
there are periods you are just waiting for the agents to all work but you can't really focus on anything else since there is always a thread which is ready with a response
my theory for this is that we are now entering the zone of “ambient work” due to the increasing capabilities of long horizon agents. you’ll be working all the time it will just be broken up by real world commitments and work is always happening in the background.
@thsottiaux two simple ones: for apps where I have a connector, codex insists on accessing through browser use even when I've added this preference to agents.md, merging chats within a folder
@willbeddow5366@HammadTime browsecomp etc are also completely saturated, models have just memorized answers for these
our internal evals focus much more on recency, freshness, multihop queries (across tasks customers care about) to actually measure retrieval capabilities
funniest thing about navier strokes drama that no one mentioned is that
Strokes and Navier also came up with their ideas independently and thought it was distinctive enough to be released separately, mirroring the language in the OAI blog weirdly similarly in spirit