pngwn

Stay tuned, we've got some huge HUGE announcement coming your way! 🤯 🤯 🤯

Super hyped to have @modal on board as a sponsor for our next hackathon! 🎉 Participants get $250 in free compute credits and a shot at winning a cool $2500 cash prize. Let’s go! 👇

working on an open-source tabular data cleaner built with the new @gradio dataframe component ✨ upload or paste your csv/tsv/txt 🧹 clean data with AI (dedupe, strip emojis, fix formatting) built with svelte + transformers.js contributions welcome! hmb-dataframe-cleaner.static.hf.space

🚨 new gradio release 🚨 we've entered the frontend arena... you can now use the @gradio dataframe as a standalone component in your svelte projects! 🧵

@sarahookr Simit, labneh, and honey ❤️ I miss turkey.

There are only two places in the world who understand the optimal way to make a bagel — Montreal bagels and simit in Turkey.

@KevinEspiritu Ah. It’s good! Same principles you mentioned here.

@evilpingwin I haven't used that yet

Everything I've learned about drawing after 78 days of teaching myself to draw from scratch:

We’re already #1 trending on @huggingface with gpt-oss! Huge thanks to the open-source AI community for the love. 🤗

And just like that, @OpenAI gpt-oss is now the number one trending model on @huggingface, out of almost 2M open models 🚀 People sometimes forget that they've already transformed the field: GPT-2, released back in 2019 is HF's most downloaded text-generation model ever, and Whisper has consistently ranked in the top 5 audio models. Now that they are doubling down on openness, they may completely transform the AI ecosystem, again. Exciting times ahead!

💬 From Replika to everyday chatbots, millions of people are forming emotional bonds with AI, sometimes seeking comfort, sometimes seeking intimacy. But what happens when an AI tells you "I understand how you feel" and you actually believe it? At @huggingface, together with @frimelle and @YJernite, we dug into something we felt wasn't getting enough attention: the need to evaluate AI companionship behaviors. These are the subtle ways AI systems validate us, engage with us, and sometimes manipulate our emotional lives. Here's what we found: 👉 Existing benchmarks (accuracy, helpfulness, safety) completely miss this emotional dimension. 👉 We mapped how leading AI systems actually respond to vulnerable prompts. 👉 We built the Interactions and Machine Attachment Benchmark (INTIMA): a first attempt at evaluating how models handle emotional dependency, boundaries, and attachment (with a full paper coming soon). 🚢 We also shipped two visualization tools on Gradio to see how different models behave when things get emotionally intense.

I don’t really do this anymore. If you wanna find me, check my pin/ bio.

Onwards to victory!!

Introducing SmolLM3: a strong, smol reasoner! > SoTA 3B model > dual mode reasoning (think/no_think) > long context, up to 128k > multilingual: en, fr, es, de, it, pt > fully open source (data, code, recipes) huggingface.co/blog/smollm3

make go fast!!

You probably want to add the image to the folder and then import that image in your svelte or JavaScript file. This should give you a path that you can use as a source. This way is preferred because it means that the bundler sees it and can add it as a dependency. Let me know if this works for you!

@Gradio what is the way to add images in the custom components frontend folder. I tried adding in the static folder under the frontend folder but the images are not rendering. Please help

need some inspiration for your prize-winning agents + mcp hackathon entry? here are some awesome ideas from the gradio team 🧵

Do you have some information about rough costs per ‘learning resource’? It might be viable for individuals with specific goals. I’d also love to see more technical details (or even open sourcing so people experiment individually). You could use a non commercial or share-alike licence if you are concerned about that.

@ben_m_somers I mayyy open up the beta with more interest but it’s mostly an experiment (one that is kind of expensive to run at scale)

Whole Earth AI is a project-based learning tool. I built it to explore two questions: 1. what new ux patterns do LLMs make possible? 2. what might the montessori method applied to software for adults look like? here's what I learned,

Control the narrative and you control everything.

I don’t think this is an ignorant take, it is a strategic attempt to cement power. We have seen it time and again, OAI have no moat, their models are matched by others. This is what the giant data centre is about. Make compute (and therefore capital) the moat.