LLM Ass Bench

Posted by fragmede 7 hours ago

14240Original

Comments

Comment by drywater2 6 hours ago

Finally, I was getting tired of seeing pelicans on a bike.

Comment by schainks 5 hours ago

Up next, Pelican ass-bench!

Comment by athrowaway3z 5 hours ago

6 months from now we'll be discussing if model training is assmaxxing.

Comment by ravenstine 5 hours ago

I'm impressed that Luna got as far as it did on max reasoning. Don't get me wrong, that's one weird looking ass, but even the top GPT model a year ago probably would have done worse based on my experience (with asking it to create meshes in general, not modeling asses... yeah, that's the ticket). Then again, I'm also not, because I've found it to be a great deal at its relatively low price point when the reasoning is set to high.

Comment by variety8675 6 hours ago

The idea that they're going to benchmaxx this in the future amuses me

Comment by sethkim 5 hours ago

Folks, we've reached the top.

Comment by bogzz 5 hours ago

It's about bottoms though...?

Comment by spottedmarley 6 hours ago

ASStra for the win!

Comment by ramon156 5 hours ago

how come opus 5.5 did so well? I'm surprised

Comment by pixl97 5 hours ago

Na, not well at all. Now Fable, fable like'em thick.

Comment by snowram 5 hours ago

Because it is ass.

Comment by ggerules 5 hours ago

Better data set?

Comment by 4 hours ago

Comment by TutleCpt 5 hours ago

The prompt that created these images doesn't mention that they want a Caucasian skin color. Huh. Racist LLMs?

Comment by comradesmith 5 hours ago

It’s only a sample of one per model

Comment by ggerules 5 hours ago

Biased data?

Comment by throwaway743 5 hours ago

Makes sense. Most look like pancake butts or shitty implants.

Comment by devinprater 4 hours ago

Next, HumanBench! Draw an entire, picture-perfect human.

Comment by Ancalagon 6 hours ago

nsfw?

but hilarious nonetheless

Comment by sanex 6 hours ago

It's ok they're wearing thongs it's not nudity.

Comment by Ancalagon 5 hours ago

still awkward when a page full of thong-covered asses pops up on my extra monitor in my open-seating arrangement office that im required to attend 4 times a week (no of course im not salty or anything)

Comment by tripleee 5 hours ago

its only awkward if you quickly close it as if embarrassed

leave it up all day so others know it's intentional

Comment by pyrale 5 hours ago

Make an all-team demo on new frontiers in benchmarking technology.

Comment by knicholes 5 hours ago

Assert your dominance

Comment by tripleee 5 hours ago

jiggle one of the butts while making eye contact with passers-by

Comment by mosselman 5 hours ago

You shouldn't ASSume a link with a name like this is sfw.

Comment by jahnu 5 hours ago

Have you tried a few toots on an air horn to indicate to your colleagues that the thing on the screen was unexpected?

Comment by 5 hours ago

Comment by dbt00 5 hours ago

Agree 2x.

Comment by danbrooks 5 hours ago

Glad my work blocked this. But can we get a NSFW tag? If this is NSFW?

Comment by comradesmith 5 hours ago

It’s fine. You’ll be fine

Comment by zulux 1 hour ago

I go to church every week. I try not to swear.

The site is fine, and it's funny to my inner 13-year-old boy.

Comment by 4 hours ago

Comment by fg137 5 hours ago

If I were you I wouldn't rush to open a website that clearly has "ass" in the title

Comment by fragmede 7 hours ago

The most important of benchmarks.

Comment by winddude 5 hours ago

haha, doing the important work!

Comment by visiondude 5 hours ago

i almost wrote a extension to block mentions of pelican bench because i find those so utterly useless. now, Assbench, on the other hand, i could get behind

Comment by 5 hours ago

Comment by sergiotapia 5 hours ago

But can we make thicc pelicans?

Comment by Rapzid 5 hours ago

We need Banana Bench next.

Comment by randomblock1 5 hours ago

Now put them on a bike.

Comment by threethirtytwo 5 hours ago

[flagged]

Comment by TutleCpt 5 hours ago

Yeah, the HR people will freak out. Any excuse for those guys to come down like a hammer.