Made a tiny tool to help turn a Bluesky handle into a DID: tools.simonwillison.net/bluesky-reso...

I like Anthropic's "contextual retrieval" suggestion for creating chunks simonwillison.net/2024/Sep/20/...

Looks like @graze.social exists already! Their programming language is a nested JSON object of filters and Boolean operations: www.graze.social/docs/editor-... bsky.app/profile/graz...

🔥 Host your apps for FREE and simplify your infrastructure! 🚀 Tired of complex cloud hosting and the recurring bills that come with it? Host locally on hardware you already own and access anywhere with a browser. It's simpler than you think! Learn how in my latest post. 🔗👇

🔥 Host your apps for FREE and simplify your infrastructure! 🚀 Tired of complex cloud hosting and the recurring bills that come with it? Host locally on hardware you already own and access anywhere with a browser. It's simpler than you think! Learn how in my latest post. 🔗👇

This week we released ModernBERT, the first encoder to reach SOTA on most common benchmarks across language understanding, retrieval, and code, while running twice as fast as DeBERTaV3 on short context and three times faster than NomicBERT & GTE on long context.

I'll get straight to the point. We trained 2 new models. Like BERT, but modern. ModernBERT. Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff. It's much faster, more accurate, longer context, and more useful. 🧵

I figured out a prompting pattern for getting Claude to produce fully self-contained Python scripts that execute with "uv run" using PEP 723 inline script dependencies - and now I can one-shot useful Python utilities with it simonwillison.net/2024/Dec/19/...

HOT 🔥 fastest, most precise, and most capable hand control setup ever... Less than $450 and fully open-source 🤯 by @huggingface, @therobotstudio, @NepYope This tendon-driven technology will disrupt robotics! Retweet to accelerate its democratization 🚀 A thread 🧵

Hey @runme.dev - love your notebook-style script execution! Any plans for Windows native support? Many of us in corporate environments need this without the WSL dependency. As a Jupyter notebooks fan, I can immediately see the value of this but a many of my use cases today would be Windows native.

Excited to share that we have just released genomenotebook 1.0 together with @trichomedoctor.bsky.social ! If you like to analyze genomics data in Jupyter notebooks this is for you. You can get beautiful genome browsers directly in your notebooks: dbikard.github.io/genomenotebo...

Non-commercial license, as usual from MSR. 🙄 And of course they don't even give you the option to pay for it.

Chat with any open source repo easily. Gitingest (free online tool) turns any GitHub repository into a single markdown file for pasting. Claude artifacts makes this 300k token output pretty easy to work with.

This is a neat new variant on RAG - no vectors, not even full-text search, instead showing the model a header hierarchy and giving it a tool to read the relevant sections My notes here: simonwillison.net/2024/Dec/6/r...

As R&D staff @ answer.ai, I work a lot on boosting productivity with AI. A common theme that always comes up is the combination of human+AI. This combination proved to be powerful in our new project ShellSage, which is an AI terminal buddy that learns and teaches with you. A 🧵

I can't begin to describe how life-changing this new project, ShellSage, has been for me over the last few weeks. ShellSage is an LLM that lives in your terminal. It can see what directory you're in, what commands you've typed, what output you got, & your previous AI Q&A's.🧵

For anyone interested in fine-tuning or aligning LLMs, I’m running this free and open course called smol course. It’s not a big deal, it’s just smol. 🧵>>

Amazing demo by Vaibhav Srivastav of structured data extraction running on an LLM that executes entirely in the browser (Chrome only for the moment since it uses WebGPU). https://simonwillison.net/2024/Nov/29/structured-generation-smollm2-webgpu/

After seeing all those toxic replies to @danielvanstrien.bsky.social , I created a small script to auto-block people. Let's use AI to moderate the replies. gist.github.com/tcapelle/00a... cc. @eugeneyan.bsky.social

Hello World from Python SDK

A dataset of 1 million or 2 million Bluesky posts is completely irrelevant to training large language models. The primary usecase for the datasets that people are losing their shit over isn't ChatGPT, it's social science research and developing systems that improve Bluesky.

I find strange that engineering the gradient radically to learn better is not a whole field.

TIL how to implement GitHub OAuth for an otherwise completely static website (HTML+JavaScript on GitHub Pages) using Cloudflare Workers: https://til.simonwillison.net/cloudflare/workers-github-oauth

✨ More Bluesky tools for power-users, curious people, and nerds. ✨ One thing that makes this place a better option for anyone wanting a more conscious social experience is its "opensource-ness." It gives us a level of freedom we haven't had since the MySpace era. I missed that. 🧵 1/10

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.

It's pretty sad to see the negative sentiment towards Hugging Face on this platform due to a dataset put by one of the employees. I want to write a small piece. 🧵 Hugging Face empowers everyone to use AI to create value and is against monopolization of AI it's a hosting platform above all.

Feels good to be mentioned on HN for engineers learning AI 🥰 Helping others is a big reason I write. Here's a list on ML/AI: ## Building AI systems • Patterns for Building LLM-based Systems: eugeneyan.com/writing/llm-... • What We’ve Learned From A Year of Building with LLMs: applied-llms.org

Small yet mighty! 💫 We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠 We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base huggingface.co/collections/...

Thanks to @simonwillison.net for improving this > forked this to add script inline metadata for the dependency and use input() and getpass() to accept the credentials - now you can run it without having to install it first with uv See comment in new gist: gist.github.com/simonw/848a3...

It is their implementation of PEP 723 - it's really handy peps.python.org/pep-0723/

I want to see a screenshot or photo of a project that you've never published anything online about before

@hamel.bsky.social has a very cool demo of using Apple Shortcuts to do cool things with AI without writing code www.loom.com/share/d19d7c...

For those waiting for news on the training of the single-GPU "DINO-like" model: About half the training is now over so let me pick some cherries for you: 🍒 🧵

Its scary to know that I am always only a click away from destroying my productivity.

This is a terrific direction for extensibility of SQL syntax. I had the luck to see @andypavlo.bsky.social discussing SQL evolution going in circles (graph db, vector db, ...), and one of the questions was on SQL dialects. Work on parsers / tooling is the answer to make SQL composable / expansible

I saw this really impressive demonstration of one/few shot learning in robotics using a graph diffusion model. If you’re interested in Robotics and AI I think it’s worth checking out! #mlsky #ai #robotics threadreaderapp.com/thread/18595... www.robot-learning.uk/instant-policy

Features from TwitterX that I'd like to see on @bsky.app: - "The bell": An option to get notified when a given user posts - Bookmarks - High-quality (and longer) video - Gathering "highlight posts" in a tab on one's own profile

Since I've been here for a while… here are some useful features on Bluesky that you might not have discovered yet! 🧵

Built my first experiment on top of Bluesky's API (actually the Jetstream WebSocket proxy) - it took ~15s of prompting in Claude to get this working: tools.simonwillison.net/bluesky-fire... More details including the prompt transcript here: simonwillison.net/2024/Nov/20/...

Just set up my M4 MacBook Pro from scratch, Marie Kondoing existing tools and exploring new options. Here's my minimal guide to setting up a new Mac. Updates include: • Oh My Zsh → Fish • iTerm → Warp • Wispr Flow, Ollama + Open WebUI, Ice Any other suggestions? eugeneyan.com/writing/mac-...

Hi everyone! I’m Mat and I work on data engineering and AI in the engineering. I love learning new things, am perpetually curious, and am passionate about technology. I started my AI journey in 2017 with fast.ai and have really enjoyed applying it to different problems.

This looks cool! Hacking on the BSKY API. Am planning on checking this out.

New here? Interested in AI/ML? Check out these great starter packs! AI: go.bsky.app/SipA7it RL: go.bsky.app/3WPHcHg Women in AI: go.bsky.app/LaGDpqg NLP: go.bsky.app/SngwGeS AI and news: go.bsky.app/5sFqVNS You can also search all starter packs here: blueskydirectory.com/starter-pack...

Hi Thomas! I’m a huge fan of how your teams share knowledge on social networks about models, datasets, and tools. That’s why I’m curating this Starter Pack: go.bsky.app/PTmCYsU

This is a really interesting thread on model scaling and quantization with a prediction that we may getting close to the scaling limit with current architectures, precision and hardware. threadreaderapp.com/thread/18563...

This was a really interesting podcast by @ericries.bsky.social . Hard to imagine the patience and perseverance required to hang on until the Generative AI explosion. Reminds me of Nvidia in some sense but Groq didn’t have gaming to tide them through until the AI revolution. youtu.be/KhLXVRiZBdo

This is a great overview of use cases for DuckDB. DuckDB is an ultra fast analytical query engine that you can run locally. If you deal with data processing for analytics or ETL and want to be able to run things locally and high performance I highly recommend you check it out.

In my blog post, I tackle @karpathy.bsky.social 'Let's build GPT' to construct a transformer 🤖 model from scratch, leveraging the foundational knowledge I gained from the fantastic @fastdotai courses by @jph.bsky.social Curious about how transformers work? blog.matdmiller.com/posts/2023-0...

Ever wondered how to supercharge your code with GPU acceleration? Check out my blog post, where I explore creating custom CUDA kernels that delivered an 8.4 million times speedup over (a naive) baseline on a real-world problem. blog.matdmiller.com/posts/2024-0...