A few weeks ago, Anthropic came out with this paper, showing how they found interpretable features in one of their models. This means that they could see which features activate when the LLM generates, and …

As the title suggests, Mozilla is experimenting with using on-device Generative AI to generate alt text. Here are some meandering thoughts.

This raises the question whether it makes sense to invest in AI generated alt-text …

A dockerised app I'm working on needs some secrets at build time. In my case, it needs to pip install from a private repository. Note that this is a generic problem, luckily with quite an …

The llm command line tool by Simon Willison lets you interact with LLMs from the command line. I've been using it recently, and while it's nice and convenient, I wasn't doing anythin I couldn't do …

When building complex workflows, I see developers getting good results with this process:

• Write quick, simple prompts and see how it does.
• Based on where the output falls short, flesh out the prompt iteratively. This …

OpenAI has recently published a document titled 'Model Spec'. It defines an ethics and norms framework models should follow. A few things that stood out:

• It surprisingly resembles Isaac Asimov's "Three Laws of Robotics", with …

TL;DR: Try Dokku if you want to run multiple toy web apps on a single server and keep the cost at minimum.

Let's talk, yet again, about deploying toy web apps. I wrote about …

TidalCycles (tidal in short) is a live coding language for music performance / composition. I don't use it myself but been playing with a live coder, Lizzie, AKA digital selves, for the last year …

bibo is a command line reference manager with a single source of truth: the .bib file. It is inspired by beets. After 3 years in the making I believe it's ready …

After more than 4 years online, the Krihelinator was shut down today. The idea behind this project was to propose an alternative to github's trading page by highlighting projects with high contribution rate instead of …