Remix.run Logo
margalabargala 4 hours ago

I suspect they're training on this.

I asked Opus 4.6 for a pelican riding a recumbent bicycle and got this.

https://i.imgur.com/UvlEBs8.png

WarmWash 4 hours ago | parent | next [-]

It would be way way better if they were benchmaxxing this. The pelican in the image (both images) has arms. Pelicans don't have arms, and a pelican riding a bike would use it's wings.

ryandrake 3 hours ago | parent | next [-]

Having briefly worked in the 3D Graphics industry, I don't even remotely trust benchmarks anymore. The minute someone's benchmark performance becomes a part of the public's purchasing decision, companies will pull out every trick in the book--clean or dirty--to benchmaxx their product. Sometimes at the expense of actual real-world performance.

seanhunter 3 hours ago | parent | prev [-]

Pelicans don’t ride bikes. You can’t have scruples about whether or not the image of a pelican riding a bike has arms.

jevinskie 3 hours ago | parent [-]

Wouldn’t any decent bike-riding pelican have a bike tailored to pelicans and their wings?

actsasbuffoon an hour ago | parent | next [-]

Sure, that’s one solution. You could also Isle of Dr Moreau your way to a pelican that can use a regular bike. The sky is the limit when you have no scruples.

cinntaile 3 hours ago | parent | prev [-]

Now that would be a smart chat agent.

mrandish 4 hours ago | parent | prev | next [-]

Interesting that it seems better. Maybe something about adding a highly specific yet unusual qualifier focusing attention?

riffraff 3 hours ago | parent | prev [-]

perhaps try a penny farthing?