This is great but does anyone know of essentially the same thing BUT it can actually get content visually? ie., it is great to have a transcript but unless the models can 'see' the video they will miss valuable info like if the in-video captions show a github repo link or something
I say this while heavily using the free money OpenAI gives out with their subs. Has anyone got a preferred provider or learnt lessons with this sort of thing?
100% - especially when there are such good providers (i.e., vercel, opencode, kilo, etc.) and the providers are getting nervous about letting people use subs for products.
It feels like all of the AI players are getting worried about proving financial viability all of a sardine... feels like the claude code scandal last week also relates