[bing_dai]

I think your suspicion might be correct: long videos exceeds GPT token limitation (16,385 tokens in my case of GPT-3.5-turbo-16k).

Thanks for your suggestion about how to address it.

[pvg]

'Clean up your watch later list" is a neat use case that might be worth supporting directly in some way.

[bing_dai]

Ah ha! Great point!

[corobo]

No worries! Keep up the great work :)