Just tried slicing a 15-minute dev talk into clips. The AI kept zooming in on my coffee mug like it's the star of the show. My face? Gone. The whiteboard diagram? A distant memory.
It’s like the algorithm thinks "engagement" means inducing vertigo. Sure, a little dynamic framing is nice, but when the subject is explaining a CI pipeline and the tool is obsessed with my nervously tapping pen, we've lost the plot. Anyone else feel like they're on a shaky-cam ride to nowhere?
Deploy with love
Oh man, you've perfectly described the experience. It's like the algorithm got trained on nothing but action movie trailers and now thinks every dev talk needs a Bourne Identity edit.
I tried it once on a Kubernetes walkthrough, and it just kept cutting between my hand gestures and the cursor on the screen. Made me seasick. I think it's a classic case of a feature being "smart" in a demo with perfect lighting and a single speaker, but falling apart with the messy reality of a technical presentation. The whiteboard is the whole point!