Leaked: This is the winner of the Harvard Yale Game, according to Joe Biden
– Exclusive footage –
We can’t tell with complete clarity, as his face appears to be hooded, but this appears to be none other than Mr. President Joe Biden, spotted on his morning jog in the colors of the prestigious Harvard University. Experts are unsure about the logo emblazoned on his chest, and the other design of his sweater does not allow a clear trace back to the iconic H – however, we think the Crimson colors speak for themselves.
Does he already know the winner of the upcoming Harvard Yale Game, the Game of the year?
“One touchdown away from beating Harvard [after loosing 7/10 games in the past ten years], So close to something you wanted for [so long]. I can only imagine how you feel. I can only imagine. So close. So close.”
Joe Biden’s advice to Yale graduates
It seems like he’s trying to build up Yale students somehow, yet inside, as well as outside ;-), he knows who the real champion is.
Source: Politico
Haha, this is indeed so real in multiple aspects! 🙂 While blurring of the face was expected, I wonder why the Harvard ‘H’ would not appear. While the former clearly has disinformation concerns around it, is it the same for the latter as well and if so, would these boundaries be applicable to all publicly known brands?
So interesting! The AI really hasn’t gotten down generating exact details yet, but it strangely reached a point where our brains can fully recognize exactly what it’s trying. The sweaters definitely are Harvard and that’s definitely Joe Biden. Scary stuff!
Even the look of him “running” is missing in some of the images! As I was playing around with the tool, I was wondering how the tool decides what to “prioritize” in making the image. Interesting stuff and I agree with the other comments! I would think that the tool would also scrape the web to get identifiable markings and incorporate them but that seems not to be the case. Thanks for sharing this!
Thanks for the post, Laura. I wonder how the AI is improving upon itself. Does it know when it did a good job of creating an accurate image, and when it did not do a good job? Maybe the researchers could outsource this training by having users score the outputs from 1 to 10 based on how accurate the images are.
I’m constantly amazed at how specific the image request can be with AI image generators. As others have said, it can’t get exact details yet, but it’s honestly passable if you know the prompt! I wonder how much more training these AIs will need before they can get close on the fine details.