Thanks for the great breakdown. I've been playing around with Gemini but hadn't seen that incredible video. Let's hope it's not a scam like the last demo
Yeah you can see they've been burned by the backlash from the last video, so in this one they're taking great care to highlight that they're speeding it up and that response time may vary. Let's see when they'll make the 1M token version available to the public.
Sora is certainly impressive. I read something about how it sort of figures out the rules of physics as it goes along... I'm not sure what all that's about, but have you read anything to that extent/in that direction?
As any AI model, it's prone to hallucination and doesn't actually "understand" anything much of what it's mimicking, which is why you still end up with videos where the laws of physics don't quite apply or objects materialize out of thin air, etc. You can see many examples in the video compilation itself.
OK, thanks. I certainly don't think it's emergent or anything like that, but I'm curious as to how it determines what makes sense (but only curious enough to pester you for instant answers, mainly).
Thanks for the great breakdown. I've been playing around with Gemini but hadn't seen that incredible video. Let's hope it's not a scam like the last demo
Yeah you can see they've been burned by the backlash from the last video, so in this one they're taking great care to highlight that they're speeding it up and that response time may vary. Let's see when they'll make the 1M token version available to the public.
Sora is certainly impressive. I read something about how it sort of figures out the rules of physics as it goes along... I'm not sure what all that's about, but have you read anything to that extent/in that direction?
As any AI model, it's prone to hallucination and doesn't actually "understand" anything much of what it's mimicking, which is why you still end up with videos where the laws of physics don't quite apply or objects materialize out of thin air, etc. You can see many examples in the video compilation itself.
OK, thanks. I certainly don't think it's emergent or anything like that, but I'm curious as to how it determines what makes sense (but only curious enough to pester you for instant answers, mainly).