Remix.run Logo
jasonjmcghee 2 hours ago

What's crazy is you've influenced them to spend real effort ensuring their model is good at generating animated svgs of animals operating vehicles.

The most absurd benchmaxxing.

https://x.com/jeffdean/status/2024525132266688757?s=46&t=ZjF...

simonw an hour ago | parent | next [-]

I like how they also did a frog on a penny-farthing and a giraffe driving a tiny car and an ostrich on roller skates and a turtle kickflipping a skateboard and a dachshund driving a stretch limousine.

jasonjmcghee an hour ago | parent | next [-]

Ok Google what are some other examples like a pelican riding a bicycle

simultsop 26 minutes ago | parent | prev [-]

reminds me of andor, luthen, positive reinforcing wasting time of emperor

threatofrain 2 hours ago | parent | prev | next [-]

Animated SVG is huge. People in different professions are worrying to different degrees in terms of being replaced by ML, but this one is huge with regards to digital art.

eurekin 2 hours ago | parent | prev | next [-]

Can't wait until they finally get to real world CAD

tngranados 2 hours ago | parent [-]

There's a CAD example in that same thread: https://x.com/JeffDean/status/2024528776856817813

tantalor 2 hours ago | parent | prev | next [-]

He's svg-mogging

gnatolf 2 hours ago | parent | prev | next [-]

So let's put things we're interested in in the benchmarks.

I'm not against pelicans!

ghurtado an hour ago | parent [-]

I think the reason the pelican example is great is because it's bizarre enough that it's unlikely that to appear in the training as one unified picture.

If we picked something more common, like say, a hot dog with toppings, then the training contamination is much harder to control.

rvnx an hour ago | parent [-]

It's the most common SVG test, it's the equivalent of Will Smith eating spaghettis, so obviously they benchmax toward it

casey2 an hour ago | parent | prev | next [-]

You don't have to benchmax everything, just the benchmarks in the right social circles

UltraSane 2 hours ago | parent | prev [-]

It if funny to think that Jeff Dean personally worked to optimize the pelican riding a bike benchmark.