| ▲ | simonw 4 hours ago |
| If anyone trains a model on https://simonwillison.net/tags/pelican-riding-a-bicycle/ they're going to get some VERY weird looking pelicans. |
|
| ▲ | suddenlybananas 3 hours ago | parent [-] |
| Why would they train on that? Why not just hire someone to make a few examples. |
| |
| ▲ | simonw 3 hours ago | parent [-] | | I look forward to them trying. I'll know when the pelican riding a bicycle is good but the ocelot riding a skateboard sucks. | | |
| ▲ | suddenlybananas 3 hours ago | parent [-] | | But they could just train on an assortment of animals and vehicles. It's the kind of relatively narrow domain where NNs could reasonably interpolate. | | |
| ▲ | simonw 2 hours ago | parent [-] | | The idea that an AI lab would pay a small army of human artists to create training data for $animal on $transport just to cheat on my stupid benchmark delights me. | | |
| ▲ | suddenlybananas 2 hours ago | parent [-] | | When you're spending trillions on capex, paying a couple of people to make some doodles in SVGs would not be a big expense. | | |
| ▲ | simonw 2 hours ago | parent [-] | | The embarrassment of getting caught doing that would be expensive. |
|
|
|
|
|
