I showed it a screen recording of the thing that I'm building. Prompted "We should refine this before I post to a social media", then walked a way making a coffee. When I got back, it unexpectedly went through the recording, decided what to keep base on the project context, added text graphic and voice narrative using another tool of mine.

Simply mind blowing. Opus could never get that done in anyway.

Ok Dario, we get it, it’s amazing.

What format was the screen recording in? So it can actually access video playback and edit that video playback and add to it via prompts?

How many tokens/$ did you end up going through for that?

Fable’s ability to understand concepts and combine different aspects together is quite impressive.

Opus keeps wondering around unrelated topics, and you find yourself scattered and constantly telling Opus to focus on the problem.

Still requires a human in the loop to make coffee...

I found it about the same, nothing special.

Can it help me organize my music collection? https://news.ycombinator.com/item?id=48637538