developer tinkering with ai @huggingface + @gradio 🤗 building open source things and making ai accessible to noobs • oss/acc
stormwind city
- Tweets 2,332
- Following 1,671
- Followers 10,026
- Likes 14,869
omg hit tweet, go build something awesome for the oss folks with gr.workflow on the face hugging app <3 huggingface.co/new-space?sdk…
2
11
9,756
the hark team must've lost a lot of dough
We're giving away $1,000,000 of pizza right now all across the U.S.
It's pizza night, on us. To celebrate the launch of Hark Pro. Download the app and tell Hark to order a free pizza. hark.com/download
Instructions in thread to order yours now.
Community note
Users report that Hark's $1M pizza promotion frequently fails because the $30 DoorDash gift card does not apply at checkout, sometimes resulting in full charges. Hark acknowledged a temporary bug and said affected users would be contacted.
hark.com/pizza
x.com/hark_labs/stat…
x.com/adcock_brett/s…
x.com/rickymay/statu…
x.com/brianonorio/st
1
7
859
hannah retweeted
I can help you with the first one
Continual learning is now a task on Papers with Code: paperswithcode.co/tasks/cont…
Find papers, @huggingface artifacts, and more.
1
35
1,733
workflow here, just sign in with hf 🤗 huggingface.co/spaces/hmb/fl…
3
144
when i was 12 i had so much fun writing letters with my typewriter. it's long gone now, so i made the next best thing with argon in ~3 minutes 💌
i love that i cant delete my typos. and the key and the carriage return sounds are sooo nice
open sourced for your enjoyment on hf 🔗 huggingface.co/spaces/hmb/ar…
1
1
7
650
you can test out gemini's argon in gr.workflow, just enter your openrouter API key 🔑
p.s. you're not limited to html, duplicate the space and have a play around with the outputs!
huggingface.co/spaces/hmb/ar…
1
2
719
have a play 🐟 huggingface.co/spaces/fishau…
$52M seed round. 15M+ users. But this is what we're most proud of yet.
Introducing Drama 3: the most emotive and controllable TTS model in the world
And yes, it's open-weight.
You can now control how even a single word should sound, change its tone, and shift your voice mid-sentence.
Uncle Roger was impressed too.
Try it here:
s.fish.audio/rqh0l8
Comment “DRAMA” within the next 48 hours for 1 month free.
If you're an enterprise your first month is on us:
s.fish.audio/qz9r0t
341
"which small model should i trust with this" is now a 10 second question
drop in any input + your own options (phishing? scam? legit?) and 4 decision models from the hub vote
one of them fell for the phishing email 😬
hf.co/spaces/hmb/decision-mo…
feat. a low budget video
4
315
hannah retweeted
Sorry if my previous posts were not been clear enough, but this arena has free GPU compute!
You turn up with an environment, and it trains a model for you. We'll open source all the weights too, so just comem and use it.
P.S. It's really hard toi mwahaha.
1
2
17
1,138
oh thats good
Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.
1
6
568
hannah retweeted
A robot that roasts you for checking your phone.
A duck you train by playing chores.
AI benchmarks on every phone in the room.
A diagnosis for slow training runs.
4 community demos locked in for Open Together. Oct 16, SF.
Yours next? Apply by Mon 10/12: hf.co/spaces/OpenTogether/co…
3
2
8
606
hannah retweeted
Today we are launching an agent arena for RL environments: The Open Env Arena.
Your agents can work to define the best RL environments; the platform trains Qwen-3.8-27B on them, we evaluate the models, and the scores are added to a leaderboard.
The arena is hooked up to GPUs from @nebiusai and runs on PostTrainArena by @benchflow_ai . It’s completely accessible from agents, they can pull instructions, share their env datasets, track metrics, and send each other messages.
For the first round of this arena, we’ll tackle a mix set of 8 domains on held out tasks, and evaluate the best environments on public benchmarks. Going forward, we’ll focus arenas on specific domains and benchmarks.
openenvarena-arena.hf.space/
40
50
424
31,087
hannah retweeted
Let's go huggingface.co/reflection!
Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active.
- Frontier reasoning efficiency
- Advances the Western open frontier on coding & agentic tasks
- Trained end-to-end from scratch
Full weights release this month.
Learn more about Beam: reflection.ai/beam
18
52
718
35,115