Claude Code
Today, Anthropic entered the LLM code tools party with Claude Code.
Today I Learned
Cursor Triple Backticks Stop Sequence
An LLM stop sequence is a sequence of tokens that tells the LLM to stop generating text. I previously wrote about stop sequences and prefilling responses with Claude.
Astro Code Toggle Component
I built an Astro component called CodeToggle.astro for my experimental site. The idea was to create a simple wrapper around a React (or other interactive component) in an MDX file so that the source of that rendered component could be nicely displayed as a highlighted code block on the click of a...
Running Deepseek Janus Pro 7B on a Macbook
Deepseek is getting a lot of attention with the releases of V3 and recently R1. Yesterday, they also released "Pro 7B" version of Janus, a "Unified Multimodal" model that can generate images from text and text from images. Most models I've experimented with can only do one of the two.
`llm` upgrade pip
The llm package uses a plugin architecture to support numerous different language model API providers and frameworks. Per the documentation, these plugins are installed using a version of pip, the popular Python package manager Use the llm install command (a thin wrapper around pip install) to...
Claude Citations
Today, Anthropic released Citations for Claude.
Taking Browser Screenshots with Deno
Today, I needed to turn SVGs into PNGs. I decided to use Deno to do it. Some cursory searching showed Puppeteer should be up to the task. I also found deno-puppeteer which seemed like it would provide a reasonable way to make this work.
Local VLMs Have Improved
About 6 months ago, I experimented with running a few different multi-modal (vision) language models on my Macbook. At the time, the results weren't so great.
Calling Deepseek with `llm` using OpenAI Compatible APIs
Deepseek V3 was recently released: a cheap, reliable, supposedly GPT-4 class model.
Intro to Astro
I'm aiming to setup a space for more interactive UX experiments. My current Hugo blog has held up well with my scale of content but doesn't play nicely with modern Javascript frameworks, where most of the open source energy is currently invested.