Prompt to video, but not cause to effect
The output of Sora, OpenAI’s latest tool, looks really impressive for an off-the-shelf tool. What I found even more interesting is that OpenAI explicitly defines the weakness of the model as not understanding “cause and effect.”
Their example is a person biting into a cookie in a video, but potentially not leaving a bite mark on the cookie. There is also a reverse treadmill scene.
Yet OpenAI downplays the absolute lack of cause-and-effect reasoning:
๐๐ต ๐ข๐๐ฎ ๐จ๐ฉ๐ง๐ช๐๐๐ก๐ ๐ธ๐ช๐ต๐ฉ ๐ข๐ค๐ค๐ถ๐ณ๐ข๐ต๐ฆ๐ญ๐บ ๐ด๐ช๐ฎ๐ถ๐ญ๐ข๐ต๐ช๐ฏ๐จ ๐ต๐ฉ๐ฆ ๐ฑ๐ฉ๐บ๐ด๐ช๐ค๐ด ๐ฐ๐ง ๐ข ๐ค๐ฐ๐ฎ๐ฑ๐ญ๐ฆ๐น ๐ด๐ค๐ฆ๐ฏ๐ฆ, ๐ข๐ฏ๐ฅ ๐ข๐๐ฎ ๐ฃ๐ค๐ฉ ๐ช๐ฃ๐๐๐ง๐จ๐ฉ๐๐ฃ๐ ๐ด๐ฑ๐ฆ๐ค๐ช๐ง๐ช๐ค ๐ช๐ฏ๐ด๐ต๐ข๐ฏ๐ค๐ฆ๐ด ๐ฐ๐ง ๐ค๐ข๐ถ๐ด๐ฆ ๐ข๐ฏ๐ฅ ๐ฆ๐ง๐ง๐ฆ๐ค๐ต.
while doubling down on its promise of AGI:
๐๐ฐ๐ณ๐ข ๐ด๐ฆ๐ณ๐ท๐ฆ๐ด ๐ข๐ด ๐ข ๐ง๐ฐ๐ถ๐ฏ๐ฅ๐ข๐ต๐ช๐ฐ๐ฏ ๐ง๐ฐ๐ณ ๐ฎ๐ฐ๐ฅ๐ฆ๐ญ๐ด ๐ต๐ฉ๐ข๐ต ๐ค๐ข๐ฏ ๐ถ๐ฏ๐ฅ๐ฆ๐ณ๐ด๐ต๐ข๐ฏ๐ฅ ๐ข๐ฏ๐ฅ ๐ด๐ช๐ฎ๐ถ๐ญ๐ข๐ต๐ฆ ๐ต๐ฉ๐ฆ ๐ณ๐ฆ๐ข๐ญ ๐ธ๐ฐ๐ณ๐ญ๐ฅ, ๐ข ๐ค๐ข๐ฑ๐ข๐ฃ๐ช๐ญ๐ช๐ต๐บ ๐ธ๐ฆ ๐ฃ๐ฆ๐ญ๐ช๐ฆ๐ท๐ฆ ๐ธ๐ช๐ญ๐ญ ๐ฃ๐ฆ ๐๐ฃ ๐๐ข๐ฅ๐ค๐ง๐ฉ๐๐ฃ๐ฉ ๐ข๐๐ก๐๐จ๐ฉ๐ค๐ฃ๐ ๐๐ค๐ง ๐๐๐๐๐๐ซ๐๐ฃ๐ ๐ผ๐๐.
Still, the model is clearly useful for a number of business applications, most obviously marketing and promotional videos. It could also be a potential game changer for the creative industries when the 60-second limit is lifted, such as museums, performing and visual arts, galleries, and fashion design.