Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 4 дней назад •via X (Twitter)

Комментарии: 25

Фото профиля Hassan
Hassan4 дней назад

Try Open Pictionary here! Built with @YoussefUiUx.

Фото профиля Hassan
Hassan4 дней назад

The code is here!

Фото профиля MusedIn
MusedIn3 дней назад

@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

Фото профиля Curious Nori | AI · Food · Travel
Curious Nori | AI · Food · Travel3 дней назад

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

Фото профиля Curious Nori | AI · Food · Travel
Curious Nori | AI · Food · Travel3 дней назад

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

Фото профиля Sacha Kleynjans
Sacha Kleynjans3 дней назад

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

Фото профиля Vero
Vero3 дней назад

@togethercompute Cool!

Фото профиля Daniel Wilson Kemp
Daniel Wilson Kemp4 дней назад

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

Фото профиля Sidecourt
Sidecourt3 дней назад

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

Фото профиля Elio科技迷(互)
Elio科技迷(互)3 дней назад

@togethercompute pictionary against muse spark open sounds fun

Фото профиля Elliott Michael Smith
Elliott Michael Smith4 дней назад

@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.

Фото профиля Hassan
Hassan3 дней назад

@togethercompute Try it and lmk what you think!

Фото профиля Elliott Michael Smith
Elliott Michael Smith3 дней назад

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

Фото профиля ThisMightWork
ThisMightWork4 дней назад

@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.

Фото профиля Abdul Wasey
Abdul Wasey4 дней назад

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

Фото профиля Alex Puzanov ❤️ AI Factory
Alex Puzanov ❤️ AI Factory3 дней назад

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

Фото профиля meshahid973
meshahid9734 дней назад

@togethercompute this is so good!

Фото профиля Hassan
Hassan3 дней назад

@togethercompute thank you!

Фото профиля Manu | 🥥
Manu | 🥥3 дней назад

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

Фото профиля StineNet
StineNet4 дней назад

@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.

Фото профиля veloX
veloX3 дней назад

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

Фото профиля Harsh Singhal
Harsh Singhal4 дней назад

@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

Фото профиля Hassan
Hassan3 дней назад

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

Фото профиля Harsh Singhal
Harsh Singhal3 дней назад

@togethercompute Yeah maybe

Фото профиля Black Label Tech
Black Label Tech3 дней назад

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

Похожие видео