1) yes! It’s not accuracy, but ndcg 2) we assume that if the agent gets the correct answer in the returned snippets it does not need to read further

Wouldn't NDCG/token results vary wildly depending on the agent's query and the number of returned items?

e.g. agents often run `grep -m 5 "QUERY"` with different queries, instead of one big grep for all items.

	▲	stephantul 7 hours ago \| parent [-]
		The same holds for semble: the agent can fire off many different semble queries with different k/parameters. I guess the point we’re trying to make is that you need fewer semble queries to achieve the same outcome, compared to grep+readfile calls.