正在加载视频...

视频加载失败

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 次观看 • 9 天前 •via X (Twitter)

25 条评论

Hassan 的头像
Hassan9 天前

Try Open Pictionary here! Built with @YoussefUiUx.

Hassan 的头像
Hassan9 天前

The code is here!

MusedIn 的头像
MusedIn9 天前

@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 的头像
Curious Nori | AI · Food · Travel9 天前

@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 的头像
Curious Nori | AI · Food · Travel9 天前

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

Sacha Kleynjans 的头像
Sacha Kleynjans9 天前

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

Vero 的头像
Vero9 天前

@togethercompute Cool!

Daniel Wilson Kemp 的头像
Daniel Wilson Kemp9 天前

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

Sidecourt 的头像
Sidecourt9 天前

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) 的头像
Elio科技迷(互)9 天前

@togethercompute pictionary against muse spark open sounds fun

Elliott Michael Smith 的头像
Elliott Michael Smith9 天前

@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 的头像
Hassan9 天前

@togethercompute Try it and lmk what you think!

Elliott Michael Smith 的头像
Elliott Michael Smith9 天前

@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 的头像
ThisMightWork9 天前

@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 的头像
Abdul Wasey9 天前

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

Alex Puzanov ❤️ AI Factory 的头像
Alex Puzanov ❤️ AI Factory9 天前

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

meshahid973 的头像
meshahid9739 天前

@togethercompute this is so good!

Hassan 的头像
Hassan9 天前

@togethercompute thank you!

Manu | 🥥 的头像
Manu | 🥥9 天前

@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 的头像
StineNet9 天前

@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 的头像
veloX9 天前

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

Harsh Singhal 的头像
Harsh Singhal9 天前

@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 的头像
Hassan9 天前

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

Harsh Singhal 的头像
Harsh Singhal9 天前

@togethercompute Yeah maybe

Black Label Tech 的头像
Black Label Tech9 天前

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

相关视频