It would be interesting to hear what you have to say now. Bard was pretty awful by the standards of the time for text. On my own channel I've compared vision models for text transcription and Claude is by far the best. I wonder if that would also apply to image critique. Anyway, thanks for the video as I'd never thought of using AI for this purpose. Much appreciated. I may very well try what you are doing here with the latest and greatest - and if i do I'll link to this as a credit for the idea (hey, you have way more subscribers than i do, but every little helps!) 😊
Yeah this was back when no other model had public multi modality usage. Done some small testing with 4o which has good results, haven’t played with Claude’s image capabilities :)
![Lethal Company Music Video 🎵 "Follow The Orders" [VERSION A]](http://i.ytimg.com/vi/QeooZB4Z7RA/mqdefault.jpg)
You deserve more followers bud.
It would be interesting to hear what you have to say now. Bard was pretty awful by the standards of the time for text. On my own channel I've compared vision models for text transcription and Claude is by far the best. I wonder if that would also apply to image critique. Anyway, thanks for the video as I'd never thought of using AI for this purpose. Much appreciated. I may very well try what you are doing here with the latest and greatest - and if i do I'll link to this as a credit for the idea (hey, you have way more subscribers than i do, but every little helps!) 😊
Yeah this was back when no other model had public multi modality usage. Done some small testing with 4o which has good results, haven’t played with Claude’s image capabilities :)