For how much I’ve seen it pushed that this model has lower hallucination rates, it’s quite odd that every actual test I’ve seen says the opposite.
Was really hoping this would be natively multimodal especially since its from open ai. but nope :/. At least the llama series does have something going for it
Surprisingly good image generation
You can set up AWS in less than 5 minutes...
It seems like there going that direction - especially the way they setup the Sora interface, It feels its nearing a video editing product.
For how much I’ve seen it pushed that this model has lower hallucination rates, it’s quite odd that every actual test I’ve seen says the opposite.
Was really hoping this would be natively multimodal especially since its from open ai. but nope :/. At least the llama series does have something going for it
Surprisingly good image generation
You can set up AWS in less than 5 minutes...
It seems like there going that direction - especially the way they setup the Sora interface, It feels its nearing a video editing product.