i opened a random lecture (MIT 14.01
Lecture 19: International Trade: Welfare and Policy)
a- i tried an exercise without watching the video, and then clicked on 'watch' next to the question, i expected it would take me to relevant portion of the video instead it played it from beginning.
b- i used the ai tutor and asked 2 random questions, instead of giving me an answer it prodded to provide more detail. this might be an intentional choice to ensure learning, however i personally prefer chatgpt's style where it gives me some information and then provides more angles to pursue.
i also asked the tutor about batman, here's the response for reference:
tell me about batman
That's a good start, but your question is very broad. When you say "tell me about Batman," are you looking for information about the character's origin, his role in comics, his significance in popular culture, or something else? Try to narrow down your question a bit.
For example, are you interested in:
- Batman's backstory and how he became a superhero?
- The different versions of Batman in comics, movies, and TV?
congrats on the shipping. this is a surprisingly tricky problem to solve.
feedback :
a- john wick is available india via lionsgate subscription in prime; while the app show only rent option. this basically means improving the scraper and channel identification in prime
b- i usually google the movie i intend to watch by appending the keyword watch. for instance, john wick watch
this works most of the time, except in cases when a particular was available on a streaming service when google scraped the page, but has since moved to a different service. if you can somehow solve for this then you'll have an edge.
it would be helpful to know which models where used in each scenario, otherwise this can largely be ignored