New NVIDIA paper says AI models do not always need huge amounts of past conversation history (context) to work well. They show that regularly shortening the history (compaction) keeps accuracy almost the same on hard, long tasks.

you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 5 hours ago

Idk on open webui with the default settings I found it really confuses the model

  • source