How dare people say neural networks generalize when it's all clearly in the training data? /ß
It means they're good at writing SVGs, in particular SVGs of animals riding modes of transport!
Absurd to think pelicans translate to coding performance. I don't care about coding! I need to generate a large volume of high quality pelican SVGs
Making SVGs is coding (of a very specific markup language). So it's not actually absurd. We've also seen that more capable models are generally better at everything minus benchmark contamination (benchmaxxing) anomalities.