Sora for the Delay OpenAI made a big splash when it showed off its new video generator Sora last month. The text-to-video model can be used to “create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions,” according to OpenAI CEO Sam Altman. And with stunning results, from a camera gliding through a snowy scene to photorealistic wooly mammoths. One catch: though we’ve seen its outputs, the tool remains internal, and until now there’d been no hint of when it might be publicly released. But now, OpenAI chief technology officer Mira Murati told the Wall Street Journal that the company will publicly release Sora “later this year.” Red Team, Green Team OpenAI is still in the throes of “red-teaming” the text-to-video model, instructing testers to probe the tool for vulnerabilities and enhancing its guardrails. For instance, Murati told the WSJ that Sora likely won’t be able to generate videos of public figures or explicit nudity. Despite the big impact it made upon its reveal last month, Sora is far from perfect. A closer look at the generated video samples reveals some glaring inaccuracies, suggesting OpenAI may be overselling the tool’s real-world capabilities. While the released version of the tool will address any of these shortcomings remains to be seen. Nonetheless, Hollywood is already paying attention, with filmmaker and actor Tyler Perry announcing he was pausing an $800 million expansion of his gigantic Atlanta studio after expressing amazement at the power of…OpenAI CTO Says It's Releasing Sora This Year