alt Hacker NewsI’m guessing that there’s a system prompt at the top telling the model about its reasoning budget. So when you switch reasoning effort it busts the cache.
Replies
SoMomentary • today at 2:11 AM
That makes sense to me. The output styles work the same way.
foota • yesterday at 10:20 PM
Hmmm... Why wouldn't this be handled like other end of prompt things like the current mode?
Maybe switching effort routes you to a different rack of gpu’s which don’t have the cache