A feature we believe users would find helpful is getting to choose between a "faster" response, or a "better" response. Faster means the response would display quicker, but wouldn't be as accurate. A better response would be more accurate and closely related to the content you're viewing, but would take more time to generate.
Here's a 3 minute video of how this could work -- we'd love to get your feedback -- you can comment below this post or email feedback@storytell.ai :
And if you'd like to become an official beta tester, here's how to sign up.
Love this @ryanfritsch , thanks again for sharing. I think this implementation is sensible enough and would work for me. In most cases, I personally would choose more accurate, since the trade-off in speed between the two models is usually in 10s of seconds not minutes, and I always want the more accurate summary. <-- Something to consider when setting defaults. Speaking of defaults, would the setting I choose become my default? I'd expect so.
Well done on the execution as ever! One thing that would be helpful for me—generally when watching your progress videos—is understanding how the problem was framed and by whom. Did a group of users express that the current speed wasn't fast enough for them?
I ask because I'm a bit unsure about introducing the idea of an accuracy-to-speed trade-off. Is the difference in speed significant enough that someone would choose to sacrifice accuracy for speed?
Better should be the option all the time for accuracy