
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!

Article URL: https://www.theregister.com/2025/03/31/llm_providers_extinction/
Comments URL: https://news.ycombinator.com/item?id=43543429
Points: 17
# Comments: 6
https://www.theregister.com/2025/03/31/llm_providers_extinction/

Article URL: https://nuejs.org/blog/large-scale-apps/
Comments URL: https://news.ycombinator.com/item?id=43543241
Points: 78
# Comments: 49


Article URL: https://julian.digital/2025/03/27/the-case-against-conversational-interfaces/
Comments URL: https://news.ycombinator.com/item?id=43542131
Points: 5
# Comments: 1
https://julian.digital/2025/03/27/the-case-against-conversational-interfaces/


Article URL: https://sgnt.ai/p/hell-out-of-llms/
Comments URL: https://news.ycombinator.com/item?id=43542259
Points: 24
# Comments: 1

Article URL: https://github.com/koreader/koreader
Comments URL: https://news.ycombinator.com/item?id=43539103
Points: 30
# Comments: 1
Article URL: https://libera.chat/news/burnout
Comments URL: https://news.ycombinator.com/item?id=43541428
Points: 3
# Comments: 0