{"id":13473,"date":"2024-02-25T10:38:19","date_gmt":"2024-02-25T09:38:19","guid":{"rendered":"http:\/\/costops.com\/index.php\/2024\/02\/25\/openais-new-video-generation-tool-could-learn-a-lot-from-babies-john-naughton\/"},"modified":"2024-02-25T10:38:19","modified_gmt":"2024-02-25T09:38:19","slug":"openais-new-video-generation-tool-could-learn-a-lot-from-babies-john-naughton","status":"publish","type":"post","link":"http:\/\/costops.com\/index.php\/2024\/02\/25\/openais-new-video-generation-tool-could-learn-a-lot-from-babies-john-naughton\/","title":{"rendered":"OpenAI\u2019s new video generation tool could learn a lot from babies | John Naughton"},"content":{"rendered":"

The footage put together by Sora looks swish, but closer examination reveals its doesn\u2019t understand physical reality<\/p>\n

\u201cFirst text, then images, now OpenAI has a model for generating videos<\/a>,\u201d screamed Mashable<\/em> the other day. The makers of ChatGPT and Dall-E had just announced Sora<\/a>, a text-to-video diffusion model. Cue excited commentary all over the web about what will doubtless become known as T2V, covering the usual spectrum \u2013 from \u201cDoes this mark the end of [insert threatened activity here]?\u201d to \u201cmeh\u201d and everything in between.<\/p>\n

Sora (the name is Japanese for \u201csky\u201d) is not the first T2V tool, but it looks more sophisticated than earlier efforts like Meta\u2019s Make-a-Video AI<\/a>. It can turn a brief text description into a detailed, high-definition film clip<\/a> up to a minute long. For example, the prompt \u201cA cat waking up its sleeping owner, demanding breakfast. The owner tries to ignore the cat, but the cat tries new tactics, and finally, the owner pulls out his secret stash of treats from underneath the pillow to hold off the cat a little longer,\u201d produces a slick video clip that would go viral on any social network.<\/p>\n

Continue reading…<\/a>
\nThe footage put together by Sora looks swish, but closer examination reveals its doesn\u2019t understand physical reality
\n\u201cFirst text, then images, now OpenAI has a model for generating videos,\u201d screamed Mashable the other day. The makers of ChatGPT and Dall-E had just announced Sora, a text-to-video diffusion model. Cue excited commentary all over the web about what will doubtless become known as T2V, covering the usual spectrum \u2013 from \u201cDoes this mark the end of [insert threatened activity here]?\u201d to \u201cmeh\u201d and everything in between.
\nSora (the name is Japanese for \u201csky\u201d) is not the first T2V tool, but it looks more sophisticated than earlier efforts like Meta\u2019s Make-a-Video AI. It can turn a brief text description into a detailed, high-definition film clip up to a minute long. For example, the prompt \u201cA cat waking up its sleeping owner, demanding breakfast. The owner tries to ignore the cat, but the cat tries new tactics, and finally, the owner pulls out his secret stash of treats from underneath the pillow to hold off the cat a little longer,\u201d produces a slick video clip that would go viral on any social network. Continue reading…Technology | The Guardian<\/p>\n","protected":false},"excerpt":{"rendered":"

The footage put together by Sora looks swish, but closer examination reveals its doesn\u2019t understand physical reality \u201cFirst text, then images, now OpenAI has a model for generating videos,\u201d screamed Mashable the other day. The makers of ChatGPT and Dall-E had just announced Sora, a text-to-video diffusion model. Cue excited commentary all over the web …<\/p>\n

OpenAI\u2019s new video generation tool could learn a lot from babies | John Naughton<\/span> Read More »<\/a><\/p>\n","protected":false},"author":0,"featured_media":13474,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts\/13473"}],"collection":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/comments?post=13473"}],"version-history":[{"count":0,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/posts\/13473\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/media\/13474"}],"wp:attachment":[{"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/media?parent=13473"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/categories?post=13473"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/costops.com\/index.php\/wp-json\/wp\/v2\/tags?post=13473"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}