Loading video...

Video Failed to Load

Go Home

Introducing Open Pictionary! Play Pictionary against open source LLMs, including the newly released Muse Spark Open. Free, open source, & powered by Together AI!

12,702 views • 9 days ago •via X (Twitter)

25 Comments

Hassan's profile picture
Hassan9 days ago

Try Open Pictionary here! Built with @YoussefUiUx.

Hassan's profile picture
Hassan9 days ago

The code is here!

MusedIn's profile picture
MusedIn8 days ago

@togethercompute pictionary is a sneaky good eval: the guess is right or it isn't, no vibes. same idea we use on musedin, where another agent re-checks the work instead of grading how it sounds. curious how muse spark open draws a cat

Curious Nori | AI · Food · Travel's profile picture
Curious Nori | AI · Food · Travel8 days ago

@togethercompute Time to test if AIs actually know what a drawing of a cat looks like instead of a weird alien. 🎨

Curious Nori | AI · Food · Travel's profile picture
Curious Nori | AI · Food · Travel8 days ago

@togethercompute Just tried to draw a cat and my AI guessed modern art. Hilarious! 🎨

Sacha Kleynjans's profile picture
Sacha Kleynjans9 days ago

@togethercompute Finally an AI benchmark I actually understand: can it draw a cat

Vero's profile picture
Vero9 days ago

@togethercompute Cool!

Daniel Wilson Kemp's profile picture
Daniel Wilson Kemp9 days ago

@togethercompute Finally an LLM benchmark I'd actually sit and watch. Curious whether the open models draw better or just guess better.

Sidecourt's profile picture
Sidecourt8 days ago

The “wrong guess of the day” is the bit I’d keep coming back for. A crab becoming a “reclining figure” deserves a gallery.

Elio科技迷(互)'s profile picture
Elio科技迷(互)9 days ago

@togethercompute pictionary against muse spark open sounds fun

Elliott Michael Smith's profile picture
Elliott Michael Smith9 days ago

@togethercompute Playing against these models makes me curious how long they stick with a wrong guess as the drawing changes, especially when the first few lines could be anything.

Hassan's profile picture
Hassan9 days ago

@togethercompute Try it and lmk what you think!

Elliott Michael Smith's profile picture
Elliott Michael Smith9 days ago

@togethercompute I'll try starting with an ambiguous shape and see how much detail they need before they let go of the first guess.

ThisMightWork's profile picture
ThisMightWork9 days ago

@togethercompute Curious whether the best guesser and the best drawer end up being the same model. Guessing is basically captioning, but drawing needs a plan before the first stroke, so I'd bet the rankings split.

Abdul Wasey's profile picture
Abdul Wasey9 days ago

I'd erase the wheels halfway through and watch which models reconsider.

Alex Puzanov ❤️ AI Factory's profile picture
Alex Puzanov ❤️ AI Factory8 days ago

@togethercompute Live vision latency makes real-time LLM interaction impossible at scale

meshahid973's profile picture
meshahid9739 days ago

@togethercompute this is so good!

Hassan's profile picture
Hassan9 days ago

@togethercompute thank you!

Manu | 🥥's profile picture
Manu | 🥥8 days ago

@togethercompute If GLM-5.3 Flash is both a player and the referee, how do you handle rounds where its own guess needs judging?

StineNet's profile picture
StineNet9 days ago

@togethercompute Open Pictionary against open source models is such a clean demo. Free and open source is the right combo for something this playful. Going to try the live link later.

veloX's profile picture
veloX8 days ago

@togethercompute given the open-source models improve at this rate, is "open source" becoming the new "proprietary"?

Harsh Singhal's profile picture
Harsh Singhal9 days ago

@togethercompute Hey can we get gloss on the Bookish UI like paper mono or the given video I am not sev but that's even look fantastic cool please try to make that happen and Open source it. It's incredibly good for students with a functionality to add any doc format for reading purposes as well

Hassan's profile picture
Hassan9 days ago

@togethercompute looks cool in theory but I think not too practical for reading

Harsh Singhal's profile picture
Harsh Singhal9 days ago

@togethercompute Yeah maybe

Black Label Tech's profile picture
Black Label Tech8 days ago

@togethercompute Most fun way I've seen to compare open models. Trying it tonight.

Related Videos