Stories by simonw

Run LLMs on macOS using LLM-mlx and Apple's MLX framework

Ask HN: Is your company running any "agents", Jan 2025 edition

Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M

Anthropic's New Citations API

Generative AI – The Power and the Glory

Agents – Adapted from the AI Engineering Chapter by Chip Huyen

Things we learned about LLMs in 2024

My Approach to Building Large Technical Projects (2023)

Trying out QvQ – Qwen's new visual reasoning model

Building Python tools with a one-shot prompt using uv run and Claude Projects

Clio: A system for privacy-preserving insights into real-world AI use

Gemini 2.0 Flash: An outstanding multi-modal LLM with a sci-fi streaming mode

I can now run a GPT-4 class model on my laptop

First impressions of the new Amazon Nova LLMs (via a new LLM-bedrock plugin)

Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac

You can now run prompts against images, audio, video in your terminal using LLM

Everything I built with Claude Artifacts this week

Experimenting with audio input and output for the OpenAI Chat Completion API

Video scraping: extracting JSON from a 35s screen capture for 1/10th of a cent

NotebookLM's automatically generated podcasts are surprisingly effective

1
2
3
4
5
6
7
8
9
10