←back to thread

456 points ph4evers | 1 comments | | HN request time: 0.21s | source

I've been working on a little side project that combines Duolingo-like listening comprehension exercises with real content .

Every video is transcribed to get much better transcripts than the closed captions. I filter on high quality transcripts, and afterwards a LLM selects only plausible segments for the exercises. This seems to work well for quality control and seems to be reliable enough for these short exercises.

Would love your thoughts!

Show context
tom2948329494 ◴[] No.43545737[source]
Just a quick note – the "Configure Your Exercise" step was a bit confusing. It took me a while to figure out what “Number of Gaps” even meant, since that’s not something I’d usually think about configuring.

Also, choosing an input method felt tricky. I hadn’t used the product yet, so I didn’t really know what to pick or what would work best for me.

Once I got into the app, everything made sense, but it wasn’t clear upfront.

Maybe you could let people start with a default setup and explore the options while using it. That way, the learning happens more naturally and the config step doesn’t feel like a blocker.

replies(1): >>43545783 #
slab_city ◴[] No.43545783[source]
Not knowing what "number of gaps" means has no consequence. Just use the app.
replies(2): >>43545913 #>>43545952 #
1. setsewerd ◴[] No.43545913[source]
If that's true then why include it at all? From a UX perspective you don't want to throw a bunch of configuration options at the user before they even know what the options mean.