10-18-2026, 11:13 PM
subscribed, curious where this lands.
|
serving on Blackwell for Phi
|
|
10-18-2026, 11:13 PM
subscribed, curious where this lands.
10-18-2026, 11:18 PM
Good point. The pattern around long context has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
If you post your exact settings, people here can probably narrow it down pretty fast.
10-19-2026, 01:32 AM
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.
10-19-2026, 02:21 AM
Quote:Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. Thanks, that helps. The pattern around reranking has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. |
|
« Next Oldest | Next Newest »
|