@simon neat!
Where can I look at the code behind this function?
Posts
-
I added multi-modal (image, audio, video) support to my LLM command-line tool and Python library, so now you can use it to run all sorts of content through LLMs such as GPT-4o, Claude and Google Gemini -
Anthropic's https://@simon would be cool to see Llama 3.2 1B or similar doing it right inside the browser
-
Anthropic released a fascinating new capability today called "Computer Use" - a mode of their Claude 3.5 Sonnet model where it can do things like accept screenshots of a remotely operated computer and send back commands to click on specific coordinates...@simon how different is that "computer use" from
GitHub - lavague-ai/LaVague: Large Action Model framework to develop AI Web Agents
Large Action Model framework to develop AI Web Agents - lavague-ai/LaVague
GitHub (github.com)
-
I exported my Claude data to poke around with it and found out I've become a HEAVY user of Claude Artifacts - the feature that lets Claude build a full interactive HTML+JavaScript tool for you based on your prompts.@simon neat!
BTW, have you tried sqlite-vec yet (sqlite as a vector database)?
GitHub - asg017/sqlite-vec: A vector search SQLite extension that runs anywhere!
A vector search SQLite extension that runs anywhere! - asg017/sqlite-vec
GitHub (github.com)
-
I finally managed to get the Llama 3.2 and Phi 3.5 vision models to run on my M2 Mac laptop, using the mistral.rs Rust library and its CLI Tool and Python bindings https://simonwillison.net/2024/Oct/19/mistralrs/@simon also, since the h20 models are available as safetensors, it should be possible to run with mlx on Mac.
I haven't looked into this rust inferencing engine you wrote about in the OP above. Would you know what model file formats does it support?
-
I finally managed to get the Llama 3.2 and Phi 3.5 vision models to run on my M2 Mac laptop, using the mistral.rs Rust library and its CLI Tool and Python bindings https://simonwillison.net/2024/Oct/19/mistralrs/@simon no, not yet.
I'm yet to look into the model files, but if they're available as gguf or onnx, it should be possible to run with llama.cpp or wllama for gguf and Transformers.js for onnx.
It's also possible to convert gguf files for running with ollama.
-
I finally managed to get the Llama 3.2 and Phi 3.5 vision models to run on my M2 Mac laptop, using the mistral.rs Rust library and its CLI Tool and Python bindings https://simonwillison.net/2024/Oct/19/mistralrs/@simon did you see that h2o.ai did well even with 0.8B model?
-
Was trawling through the Superfund-worth trace from another super high profile Next.js site, and realised that the best way to describe contemporary frontend is inconsiderate.@slightlyoff came across McMaster.com today.
-
Was trawling through the Superfund-worth trace from another super high profile Next.js site, and realised that the best way to describe contemporary frontend is inconsiderate.@slightlyoff this is awesome! Thanks a ton!
UK gov websites aren't relatable to many developers not living there, though I do understand why gov websites need to be so in the first place.
Is there a way to evaluate how do Indian gov.in/nic.in websites fare?
-
Was trawling through the Superfund-worth trace from another super high profile Next.js site, and realised that the best way to describe contemporary frontend is inconsiderate.@slightlyoff any good examples that aren't js first but are still feature rich? To help differentiate via show and tell instead of me fumbling to convey the point adequately?