pngwn @evilpingwin

(^)﹥ find me at the pin 🦋 pngwn.at 🏖️ Joined February 2009

Tweets

2K
Followers

1K
Following

392
Likes

2K

Gradio @Gradio

3 weeks ago

Join us on June 10th for a session with @cohere_Labs where we will learn how to get the best out of @cohere Tiny Aya and Transcribe models. This community event is part of Build Small Hackathon but everyone is welcome!

3 10 46 16K 12

View Details

Gradio @Gradio

8 months ago

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

3 4 37 5K 6

View Details

Gradio @Gradio

8 months ago

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! 👇

1 5 24 4K 9

View Details

hannah @erhannah

10 months ago

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

0 5 13 3K 6

View Details

hannah @erhannah

10 months ago

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

1 8 29 6K 5

View Details

pngwn @evilpingwin

10 months ago

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

0 0 2 73 0

View Details

pngwn @evilpingwin

10 months ago

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

0 0 0 171 0

View Details

Romain Huet @romainhuet

11 months ago

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

clem 🤗 @ClementDelangue

11 months ago

36 93 649 130K 69

10 2 113 8K 6

View Details

clem 🤗 @ClementDelangue

11 months ago

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!

36 93 649 130K 69

View Details

Giada Pistilli @GiadaPistilli

11 months ago

💬 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.

5 8 37 7K 18

View Details

pngwn @evilpingwin

11 months ago

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

0 0 2 249 0

View Details

pngwn @evilpingwin

12 months ago

Onwards to victory!!

🍉 Abubakar Abid @abidlabs

12 months ago

After a lot of excellent profiling and compressing by @evilpingwin, we were able shrink your Gradio app to just 1/5th of its size! It took longer than we thought it would, but I think you'll be pleased with the results! 𝚙𝚒𝚙 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 --𝚞𝚙𝚐𝚛𝚊𝚍𝚎 𝚐𝚛𝚊𝚍𝚒𝚘

0 4 20 4K 2

0 2 9 2K 0

View Details

Loubna Ben Allal @LoubnaBenAllal1

12 months ago

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

66 202 1K 280K 526

View Details

pngwn @evilpingwin

a year ago

make go fast!!

🍉 Abubakar Abid @abidlabs

a year ago

🔥 We crushed some serious bytes in Gradio 5.35, coming out soon! From 7.4 MB → 983 KB client-side From 1.4 MB → 275 KB over the wire

3 2 31 10K 5

0 1 7 2K 0

View Details

pngwn @evilpingwin

a year ago

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!

1 0 0 19 0

View Details

Gradio @Gradio

a year ago

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

5 14 41 45K 42

View Details

pngwn @evilpingwin

a year ago

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.

0 0 0 35 0

View Details

pngwn @evilpingwin

a year ago

Control the narrative and you control everything.

0 0 1 124 0

View Details

pngwn @evilpingwin

a year ago

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.

TBPN @tbpn

a year ago

We asked @rabois about AI insights from the most recent KV Summit at @khoslaventures. "@altcap spoke about this: there's only going to be one foundation model research lab that'll be a successful winner." "VCs shouldn't invest there. There's more room for VCs at the application