adishj

no worries at all. compared to some other comments in this thread, I didn't find your tone snarky at all. I appreciate your engaging with the conversation and the thread :)

Hey there, this is just the output from the Rough Cut tile. Right now each tile in Mosaic represents a modular and functional edit to the video. So after you've got your Rough Cut, given all your footage, there are other tiles which you can then use to add transitions, motion graphics, background music, etc.

That being said, the coolest part with this Rough Cut was that it decided to stand in the footage of the kite to creatively imply the freefall portion of the skydive (because we aren't able to record while we're jumping out of a plane). This ability for it to creatively decided to imply the jump because of the limited footage is what I wanted to get across here.

curious how does this compare to something like Memories.ai when it comes to video in particular?

Hey there! We already support XML exports to DaVinci Resolve, Final Cut Pro, and Premiere Pro!

We also do transcoding of all uploaded files to lower-res proxies, which can be re-linked when brought back into a more traditional NLE.

good point — we could enable these more granular-level knobs for users if it seems to be something people want

since we're building on top of LLMs which are by nature probabilistic, you won't produce the exact same frame-level cut each time, but of course there is still determinism in the expected outputs

for example, if you have a workflow setup to create 5 clips from a podcast and add b-rolls and captions and reframe to a few different aspect ratios, any time you invoke this workflow (regardless of which podcast episode you're providing as input), you'll get 5 clips back that have b-rolls, captions, and are reframed to a few different aspect ratios

however, which clips are selected, what b-rolls are generated, where they're placed — this is all non-deterministic

you can guide the agent via prompting the tiles individually, but that's still just an input into a non-deterministic machine

what I mean here is that processing / analyzing a beefy file format like video will take longer than processing text input

same with returning that back to the user as manipulated output (text / code generation is much more rapid than rendering a video)

thanks dan

thanks for the kind word and for being an early supporter!

thanks for the kind word and for being an early supporter!

Haven't chatted with them but their platform looks interesting!

Video is hard, but it's also a fun modality which presents some interesting challenges. And is where content is converging towards.

next dropbox? lets go!

loom is focused on screen recordings / demos

great to hear — I'd recommend using the clips tile to create clips, but you can also use the rough cut tile to help edit down the raw footage for the long-form