This is such a common annoyance on the modern internet. I've recently been playing Minecraft with my kids, with a few mods, and I've been irritated to discover that - unlike when I'd mess around with mods a decade ago - lots of the "documentation" for mods now exists only in video form.
Anyway, I built / slopped out this little wrapper for yt-dlp that I call tuber[1], and it has a feature for grabbing a video's subtitles and summarizing them with Claude, if you've got the CLI. I've found it really handy for those annoying cases where some video seems to promise info I want but I don't want to sit through ten minutes of bullshit.
you could also use openai whisper for transcription. takes longer but beats bad subtitles
Obviously lawyers should not be cheating with AI, especially when they don't even check it. But it does sound to me as if this is an opportunity to re-factor the process. We're carrying forward some ideas originally implemented in Latin, and which can be dramatically simplified.
I'm not a lawyer; I know this only in passing. And I am aware that there are big differences between law and code. But every time I encounter the law, and hear about cases like this, what I see are vast oceans of text that can surely be made more rigorous. AI is not the problem; it's pointing out the opportunity.