Testing how well AI coding agents use various test and verification techniques to improve software quality.
6th September 2026 - Link Blog Research acceleration: The view inside OpenAI. Apparently today is RSI day at OpenAI, for Recursive Self-Improvement -
This is the last article in the series. Two dashboards left: MVP, which answers “are we done yet”, and Developers, which answers “what is everybody pr
6th September 2026 - Link Blog The purpose of DNS is to spread scams. Terence Eden shares some daunting statistics in support of his take that "the Do
6th September 2026 Comment My comment on There's No Limit to How Bad Code Can Get — Lobste.rs [In reply to a comment about burning it down to start fr
Simon Willison’s Weblog Subscribe Sponsored by: Portnox — Shadow AI is the new shadow IT. On Sept. 10, Forrester Research and Portnox share practical
TL;DR A private AI model factory is not simply a cluster of GPU servers. It is a governed operating model that turns approved enterprise data into tes
Expo Router’s submodule NativeTabs renders a real Material 3 navigation bar on Android and its native counterpart on iOS from one component tree. On A
AI and Digital Poverty: Bridging or Widening the Divide?AI and Digital Poverty: Bridging or Widening the Divide?Artificial intelligence is transformin
OpenAI introduces GPT-6 Astra for developers, highlighting improved attention to detail, prompt understanding, and 3D model generation capabilities.
Migrating Agents to Foundry Posted on September 5, 2026 by Jesse Liberty I wanted to deploy my demonstration program, a local console application, to
The previous post discussed the motivation for and application of the rank-trace theorem. This post will give a proof. Suppose A is a real symmetric m
This is the fourth of the five GitHub dashboards and the one I use most. Where Release answers what is about to ship and Sprint answers how the fortni
5th September 2026 TIL Using Blender with coding agents on macOS — Modern frontier models have got *really good* at using Blender. I've been having a
Whenever I have an idea, I talk to an LLM. But I don’t ask it to tell me whether the idea is good. Instead, I give it the half-baked thought and ask i
TL;DR The VCF AI Atlas is a mental model for designing private AI as a governed set of territories rather than one oversized cluster. Training, infere
Four years and 210 weekly issues taught me more than the topics did. The four lessons I keep coming back to are the ones this issue walks through: con
In part one, PulseOps hit its first distributed-systems problem. Two API replicas each owned their own cache, so the same service could look healthy t
In a study published in 2019, researchers put adults who had played Pokémon extensively as children into an fMRI scanner. When those adults looked at
A self-hosted assistant is only useful if you can reach it safely when you are away from your desk. This setup gives Hermes Agent a private, encrypted
