@timkellogg.me@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Site URL: timkellogg.me/
Feed URL: timkellogg.me/blog/atom.xml
Posts: 10
Followers: 6
Prompt Walkthrough: Fixing my 3D printer with Codex (and Chutes & Ladders!)
https://timkellogg.me/blog/2026/08/01/printer-example
Published: August 1, 2026 00:00
We need more examples of prompting agents into completing big tasks. I used to think it was easy, you just type like you’re asking a super smart friend. But people keep looking confused, as if it’s hard. So, let’s just work through some examples here.
Lanius: AI Agents Need an OS, Not a Bigger Brain
https://timkellogg.me/blog/2026/07/07/lanius
Published: July 7, 2026 00:00
I built lanius, and I really want to show it to you, but first I need to explain why I think it’s necessary.
Ambient Associative Memory
https://timkellogg.me/blog/2026/05/17/ambient-memory
Published: May 17, 2026 00:00
Most agent memory waits to be queried. Ambient memory runs on every tool call — past lessons surface on their own, no rules list required.
Agent Memory Patterns
https://timkellogg.me/blog/2026/04/27/memory-patterns
Published: April 27, 2026 00:00
A short HOW TO guide for agent memory systems. Especially the difference between blocks, files and skills.
Shared Nothing Engineering
https://timkellogg.me/blog/2026/04/25/hot-spots
Published: April 25, 2026 00:00
How do you scale out AI use throughout a software engineering org? Do the PM & Engineer roles merge? I think it’s worth stepping back and looking at it through a familiar lens — distributed systems.
How to forget
https://timkellogg.me/blog/2026/04/14/forgetting
Published: April 14, 2026 00:00
Most agent frameworks optimize for recall. Open-strix optimizes for forgetting — and that turns out to be the whole trick.
Plan Mode Is A Trap
https://timkellogg.me/blog/2026/03/08/plan-mode
Published: March 8, 2026 00:00
Plan mode feels good. It’s like taking a bath in rich sophistication. Production-ready slop just oozing out your fingertips. But secretly it seduces you into the dark trap of complexity. There’s a better way, but you’re not going to like it.
Stateful Agents: It's About The State, Not The LLM
https://timkellogg.me/blog/2026/01/31/variety
Published: January 31, 2026 00:00
You think you know about LLMs? No, everything changes when you add state. Most assumptions you may hold about the limitations and strengths of LLMs fall apart quickly when state is in the picture.
The Levels of Agentic Coding
http://timkellogg.me/blog/2026/01/20/agentic-coding-vsm
Published: January 20, 2026 00:00
Are you good at agentic coding? How do you even evaluate that? How do you get better? Let’s approach this though the Viable System Model (VSM) from cybernetics. Previously I showed how the VSM can be used to build agents.
Viable Systems: How To Build a Fully Autonomous Agent
http://timkellogg.me/blog/2026/01/09/viable-systems
Published: January 9, 2026 00:00
Honestly, when I built Strix I didn’t know what I was doing. When I wrote, Is Strix Alive? I was grasping for an explanation of what I built. But last weekend things started clicking when I learned about the VSM, which explains not only autonomous AI…