iiinova — where your digital self keeps evolving

Nathan Sarrazin @nsarrazin.com · 09/12/2025

Super basic but watching the sunset by the cross of the martyrs was super nice and the O’Keeffe museum was also great. + you have to get a Frito pie at five & dime!

140

Nathan Sarrazin @nsarrazin.com · 22/09/2025

Lil personal update: I started a new role at Apple this month! 🍏 I'll be doing full-stack work, building tooling for AIML teams. Excited for what's to come :)

081

Nathan Sarrazin @nsarrazin.com · 01/09/2025

LLMs are good at boilerplate thanks to repetition in the training data. What makes Svelte great (imo!) is how little boilerplate there is. I worry there’s an unsolvable tension between tools that feel great to use by hand vs feel great to use with LLMs. The latter being mostly busywork

120

Nathan Sarrazin @nsarrazin.com · 26/08/2025

Thanks! It's inspired by 0x10c, teenage me couldn't let go of the fact that they never finished the game, so now that I know a little more I'll just make my own version :)

010

Nathan Sarrazin @nsarrazin.com · 26/08/2025

Ended up pushing it here: spesscomputer.nsarrazin.com It's just a proof of concept at this stage but I'm already amazed it's possible to do this in a browser, godot is pretty wild. Need to add support for interrupts on the 6502 side of things and uuh *just* make a fun game out of it.

spesscomputer.nsarrazin.com

SpessComputer - 6502 Assembly Space Computer Simulator

Program a retro 6502-based space computer to control spacecraft in this interactive programming simulator. Write assembly code, manage memory, and navigate through space.

000

Nathan Sarrazin @nsarrazin.com · 23/08/2025

thanks! i'm still thinking about how hard to make it, should players figure out orbital parameters from first principles using stuff like star/horizon sensors or do I "cheat" a little and directly expose velocity for example ? don't want it to be overwhelming but not too easy either

000

Nathan Sarrazin @nsarrazin.com · 22/08/2025

It's open-source here: github.com/nsarrazin/sp... It runs entirely in the browser so I'll be publishing it soon, it's absolutely not ready for release but it's been a fun learning experience. I still need to figure out how to make a fun game out of this, not sure what the gameplay loop could be.

github.com

GitHub - nsarrazin/spesscomputer

Contribute to nsarrazin/spesscomputer development by creating an account on GitHub.

140

Nathan Sarrazin @nsarrazin.com · 22/08/2025

I've been working on a little game project recently, controlling a spacecraft using a 6502 emulator! You can read sensors and actuate the craft by doing read/writes to memory. It's a Godot project (with a 6502 rust extension) exported to the web with a svelte interface. A lot of firsts for me 😅

4256

Nathan Sarrazin @nsarrazin.com · 26/04/2025

Unfortunately the communities best suited to create such feeds are being alienated from the platform 🫠

020

Nathan Sarrazin @nsarrazin.com · 26/04/2025

Yeah I feel like custom feeds could really solve this, seems like there is a lot of untapped potential in building open recommendation systems that are transparent and customizable. Most feeds I've seen are really basic heuristics and miss out on discoverability

140

Reposted by Nathan Sarrazin

Yacine Jernite @yjernite.bsky.social · 16/04/2025

Today in Privacy & AI Tooling - introducing a nifty new tool to examine where data goes in open-source apps on @hf.co 🤗 HF Spaces have tons (100Ks!) of cool demos leveraging or examining AI systems - and because most of them are OSS we can see exactly how they handle user data 📚🔍 1/4 🧵

Interface of Space Privacy Analyzer app, describing how it reviews Hugging Face Spaces for data privacy concerns, with a pre-loaded example for the Hugging Face demo app for SmolVLM2

A TLDR report generated by the Spaces Privacy app outlining the different types of data used and where they go when using the app

174

Reposted by Nathan Sarrazin

Andi @andimara.bsky.social · 08/04/2025

Today, we share the tech report for SmolVLM: Redefining small and efficient multimodal models. 🔥 Explaining how to create a tiny 256M VLM that uses less than 1GB of RAM and outperforms our 80B models from 18 months ago! huggingface.co/papers/2504....

huggingface.co

Paper page - SmolVLM: Redefining small and efficient multimodal models

Join the discussion on this paper page

2218

Reposted by Nathan Sarrazin

jsulz @jsulz.com · 18/03/2025

Last week, we launched a waitlist to move builders on @hf.co from LFS to Xet. This was made possible through months of hard work and staged migrations to test our infrastructure in real-time. This post provides an inside look into the day of our first migrations and the weeks after.

huggingface.co

Xet is on the Hub

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

1113

Reposted by Nathan Sarrazin

Erik @erikkaum.bsky.social · 12/03/2025

Gemma 3 is live 🔥 You can deploy it from endpoints directly with an optimally selected hardware and configurations. Give it a try 👇

162

Reposted by Nathan Sarrazin

Margaret Mitchell @mmitchell.bsky.social · 04/03/2025

🤖 (🤗+🐸 )=✅ I am always stoked to share how the tech world operationalizes ethical values, and I get to do that today. 🥳 @hf.co and JFrog have partnered to certify models for security and safety. This also moves forward AI *trustworthiness* and provides another form of AI *transparency*. More later!

businesswire.com

JFrog and Hugging Face Team to Improve Machine Learning Security and Transparency for Developers

JFrog Ltd (Nasdaq: FROG), the Liquid Software company and creators of the JFrog Software Supply Chain Platform, today announced it is partnering with

02911

Nathan Sarrazin @nsarrazin.com · 01/02/2025

As someone building for the self hosting crowd, the main benefit is the assurance that my app will work across all kind of setups. I'd be open to support alternatives but I genuinely don't know any 😅 What would be your ideal distribution method for full stack apps?

120

Nathan Sarrazin @nsarrazin.com · 12/01/2025

This felt like a good use case for reasoning models (better ability to detect its own mistakes especially around things like letter manipulations which are naturally challenging for LLMs) and indeed:

A screenshot of the chatgpt app, showing a conversation with the o1 model.

The user asks: What's the name of a four letter animal that, when reversed becomes the name of a plant ?

And the model answered: A neat example is “deer,” which reverses to “reed.”

070

Nathan Sarrazin @nsarrazin.com · 08/01/2025

So mastermind is wordle but only for one possible combination

110

Nathan Sarrazin @nsarrazin.com · 30/12/2024

Remember those .io games which were "multiplayer" but were actually just bots? Everyone could feel like they were winning regardless of their skill level! Social networks are 0-sum game for attention but this will make sure you get replies & likes from fake people to keep you hooked & posting.

130

Reposted by Nathan Sarrazin

Svelte @svelte.dev · 17/12/2024

Day 17 — until today, intellisense would often fail when you were in the middle of writing components, because Svelte's parser crashed on syntax errors. We just fixed that. Install svelte@latest, make sure your extensions are up to date, and feel the wind in your hair as you write your components

611211

Reposted by Nathan Sarrazin

Thomas Wolf @thomwolf.bsky.social · 14/12/2024

2025 will be the year of AI for science Leveraging all the things we've recently learned training AI models for 1000x impact in science and this will need data! More details: huggingface.co/blog/lemater... Thread: ...

26211

Nathan Sarrazin @nsarrazin.com · 12/12/2024

Naturally it makes me want to move some of the logic away from my components to .svelte.ts classes... I'm not sure if that's going to be more maintainable long term: having logic, layout and styling into a component was a big plus for Svelte imo. I guess I just need to experiment with it more?

000

Nathan Sarrazin @nsarrazin.com · 12/12/2024

This feels like a pretty big deal! Loving this new feature, especially when combined with reactive state in classes. I really like this new Svelte DX

130

Reposted by Nathan Sarrazin

narsilou.bsky.social @narsilou.bsky.social · 10/12/2024

Performance leap: TGI v3 is out. Processes 3x more tokens, 13x faster than vLLM on long prompts. Zero config !

1196

Nathan Sarrazin @nsarrazin.com · 06/12/2024

New Llama model just dropped! Evals are looking quite impressive but we'll see how good it is in practice. We're hosting it for free on HuggingChat, feel free to come try it out: hf.co/chat/models/...

hf.co

meta-llama/Llama-3.3-70B-Instruct - HuggingChat

Use meta-llama/Llama-3.3-70B-Instruct with HuggingChat

0101

Reposted by Nathan Sarrazin

Lichess @lichess.org · 06/12/2024

The Lichess database of games, puzzles, and engine evaluations is now on @hf.co - huggingface.co/Lichess. Billions of chess data points to download, query, and stream and we're excited to see what you'll build with it! ♟️ 🤗

39423

Nathan Sarrazin @nsarrazin.com · 02/12/2024

Currently it's only available with Qwen's QwQ preview. I'm hopeful we'll have more open reasoning models in the future though! Try it out here for free: huggingface.co/chat/models/...

huggingface.co

Qwen/QwQ-32B-Preview - HuggingChat

Use Qwen/QwQ-32B-Preview with HuggingChat

020

Nathan Sarrazin @nsarrazin.com · 02/12/2024

Worked on a little UI for displaying the outputs of reasoning models on HuggingChat... Trying to find the right balance between letting users see the raw model output but also making the final answer easier to parse. QwQ can be *very* verbose so it seemed useful to give a summary at the end.

251

Reposted by Nathan Sarrazin

Jeremy Howard @howard.fm · 28/11/2024

Did you know that 99% of email today is spam? Your inbox isn’t 99% spam because AI is used to filter it. The same 99% will happen here too, but if AI researchers continue to get perma-banned for making available the datasets needed to filter it, it’s going to make this platform unusable.

4251064

Nathan Sarrazin @nsarrazin.com · 29/11/2024

We already support some other modalities like image & speech (technically video too) in the form of tools: huggingface.co/chat/tools You can activate them and then call them from your chats with any model that's tool-calling compatible.

huggingface.co

HuggingChat - Tools

Browse HuggingChat tools made by the community.

000

Nathan Sarrazin @nsarrazin.com · 28/11/2024

We just deployed Qwen/QwQ-32B-Preview on HuggingChat! It's Qwen's latest experimental reasoning model. It's super interesting to see the reasoning steps, and with really impressive results too. Feel free to try it out here: huggingface.co/chat/models/... I'd love to get your feedback on it!

huggingface.co

Qwen/QwQ-32B-Preview - HuggingChat

Use Qwen/QwQ-32B-Preview with HuggingChat

1397

Nathan Sarrazin @nsarrazin.com · 26/11/2024

Adding comments can be done with a single line of code. Really impressed by how easy it is to build on top of the network so far!

062

Nathan Sarrazin @nsarrazin.com · 26/11/2024

Built something a little different: github.com/nsarrazin/bs... A svelte 5 component you can easily add to your blog/project to create a comment feed from a Bluesky discussion. Supports filtering logic & sorting by likes or recent. Styling is completely customizable thanks to Svelte 5 snippets!

github.com

GitHub - nsarrazin/bsky-comments-svelte: A simple customizable Svelte 5 component to add comments to your website using Bluesky

A simple customizable Svelte 5 component to add comments to your website using Bluesky - nsarrazin/bsky-comments-svelte

282

Nathan Sarrazin @nsarrazin.com · 01/11/2024

It's the official french spelling for some reason... You won't find "espresso" in a french dictionary: www.larousse.fr/dictionnaire...

120