undefined | Better HN

0 pointsenraged_camel4mo ago0 comments

I am also trying to understand the difference between compaction, and what IDEs like Cursor do when they "summarize" context over long-running conversations.

Is this saying that said summarization now happens at the model level? Or are there other differences?

0 comments

typpilol4mo ago

Afaik, there's no difference besides how aggressive or not it is.

But it's the same concept. Taking tokens in context and removing irreverent ones by summarizing, etc

baby4mo ago

Codex couldnt do what claude did before when reaching full context window

j / k navigate · click thread line to collapse