Bookmarks

Someone on Hacker News asked for tips on setting up a codebase to be more productive with AI coding tools. Here's my reply: Good automated tests which the coding agent …

One of the most controversial things I believe about good software design is that your code should be more flexible than your domain model. This is in direct…

When designing software systems, do the simplest thing that could possibly work. It’s surprising how far you can take this piece of advice. I genuinely think…

The big idea of James C. Scott’s Seeing Like A State can be expressed in three points: Modern organizations exert control by maximising “legibility”: by…

I have shipped a lot of different projects over the last ~10 years in tech. I often get tapped to lead new ones when it’s important to get it right, because I’m…

Reproducibility is a bedrock of scientific progress. However, it’s remarkably difficult to get reproducible results out of large language models. For example, you might observe that asking ChatGPT the same question multiple times provides different results. This by itself is not surprising, since getting a result from a language model involves “sampling”, a process that converts the language model’s output into a probability distribution and probabilistically selects a token. What might be more surprising is that even when we adjust the temperature down to 0This means that the LLM always chooses the highest probability token, which is called greedy sampling. (thus making the sampling theoretically deterministic), LLM APIs are still not deterministic in practice (see past discussions here, here, or here). Even when running inference on your own hardware with an OSS inference library like vLLM or SGLang, sampling still isn’t deterministic (see here or here).

hi, i'm jenn schiffer and this is my lifestyle blog

I gave a talk last night at Claude Code Anonymous in San Francisco, the unofficial meetup for coding agent enthusiasts. I decided to talk about a dichotomy I’ve been struggling …

Learn how Claude Code's new sandboxing feature protects developers with filesystem and network isolation, reducing permission prompts and increasing user safety.

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Digital Signage OS, to use a Raspberry Pi or x86 PC to display a webpage, in fullscreen, reliably, 24/7

Here's how to find Comet Lemmon in October's night sky.

Low tech can be geopolitically significant too

Exploring what's interesting about UUIDv7 support using a demo crab store.

In a world where corporations have detached buying from owning, one man attempts to do something radical: build his own cloud.

A practical guide to working with AI coding agents without the hype.

Claude Haiku 4.5, our latest small model, is available today to all users.

The umbrella project behind Incus, LXC, LXCFS, Distrobuilder and more.