[naikrovek]

they can, they just can't do it well. at no point does any LLM understand what it's doing.

[kblissett]

If you think they can't do this task well I encourage you to try feeding ChatGPT some long documents outside of its training cutoff and examining the results. I expect you'll be surprised!

[kayodelycaon]

It can produce something that looks like a summarization based on similarly matching texts.

Depending how unique the text is determines how accurate the summarization is likely to be.