Artificial intelligence is still in its infancy among the general public, but already it's making a big impression. This is true for ChatGPT, but also for all the applications capable of generating images from simple suggestions, or even videos from the same kind of suggestions.
The following sequence, showing an old Land Rover on an off-road trail, gives us another idea of the power of artificial intelligence.
You can tell the whole thing is AI-generated by looking at the Danover name on the model instead of Land Rover or Range Rover. Still, the video is quite convincing, and if you don’t look too closely you might think this was made by a film crew.
The video was developed by Sora, part of the OpenAI group, the research firm behind ChatGPT and DALL-E, which converts text into images. For Sora, the ability to transform text into a video sequence was announced this week.
It's as impressive and not a little disconcerting, because it begs the question of what this means in the long run for creators of real video content.
By the way, here’s the text used to generate the 20-second video shared by Sora:
“The camera follows behind a white vintage SUV with a black roof rack as it speeds down a steep dirt road surrounded by pine trees on a steep mountain slope, dust rises from its tires, the sunlight shines on the SUV as it speeds along the dirt road, casting a warm glow over the scene. The dirt road curves gently into the distance, with no other cars or vehicles in sight. The trees on either side of the road are redwoods, with patches of greenery scattered throughout. The car is seen from the rear following the curve with ease, making it seem as if it is on a rugged drive through the rugged terrain. The dirt road itself is surrounded by steep hills and mountains, with a clear blue sky above with wispy scattered clouds.”
The folks at OpenAI explain that the technology is not yet fully developed, and that, for example, Sora may have difficulty reproducing a complex physical landscape accurately, and that she may have problems fully understanding specific instances of cause and effect. They also claim confidently that the technology will improve, and fairly rapidly.
We'll leave you to ponder this technology, which continues to impress ... and gain in influence in ways we’re only beginning to comprehend.