The idea is that you create a summary with sufficient details, or you trim things away, depending on the method, but you do in fact lose exact details.

The impacts of this are not well known and likely depend on model, harness, and session. (hunch)

▲

tbharath 8 hours ago | parent [-]

So it does forward pass once again to get the summary from the whole session as input?

	▲	verdverm 7 hours ago \| parent [-]
		There are a lot of things people do, but I don't think a forward pass is the right way to think about it, think more agent than llm