This action will delete this post on this instance and on all federated instances, and it cannot be undone. Are you certain you want to delete this post?
Community
Activity
Karl Matthias postedFeb 28, 2026
After a couple of weeks using Codex, I am pretty happy with it as a step-up improvement over Claude Code. It tends to do the right thing more frequently and without interaction, and the sandbox model prevents continuous interaction over permissions. Still not a perfect tool, of course, but I am pleased. #AI
Local-first? Offline-first? There is more to ditching The Cloud!
🍃 The leaf architecture describes apps that are:
Local
Encrypted
Autonomous
Federated
Karl Matthias postedFeb 23, 2026
Enjoying how trivial it is to improve all my development tooling and environment by having AI just write the tool I want and haven't made time for. Latest example: macOS xbar plugin that tracks both my open PRs and also review requests. It uses magick to generate nice icons that sit in the tray like this (the two numbers on the left):
Karl Matthias postedFeb 20, 2026
Our free credits with Claude (Anthropic) ran out and so I've been using Codex (OpenAI) for the last few days. It's much mellower than Claude in expression, but seems maybe more competent even. So far I am impressed.
Karl Matthias postedFeb 18, 2026
I'll be writing a blog post about this, but at Mozi we just open-sourced a tool I wrote that I've been using a lot: https://github.com/mozi-app/mermAId . It's a Mermaid live editor / MCP server that is made to interact with LLM agents while planning. The agent can push and pull Mermaid diagrams from the editor. The editor has vim bindings support if you want to use them. On macOS it's a native app, on Linux and Windows it runs a server and opens the UI in the browser. There is an accompanying CLI script for those who prefer that over MCP. The details are all in the README.
Karl Matthias postedDec 8, 2025
I spoke at the Augmented Software Engineering meetup two weeks back about 6 months of agent-assisted coding with Claude. #AI #Agentic #ClaudeCode
Karl Matthias postedSep 22, 2025
The thing with the AI tools is... they are tools. It's not a sentient thing. It's a tool. And you have to learn how to use it if you want to get anything out of it. The fact that it's being sold as not-a-tool is the main issue with regard to utility. "Your virtual co-worker!" "Anyone can use it" "Just use natural language", etc. Nonsense.
Karl Matthias postedAug 29, 2025
I just asked Claude Code to diagnose an issue in code it wrote. I told it to also use Gemini on the CLI to do the same analysis. Claude was to discuss the issue with Gemini until they had a consensus on the problem. This actually worked! Kind of nutty, but the outcome was a good plan to fix it. Better than what I was getting from Claude alone.
Quote from a friend during a chat about "AI" and pareidolia: "Tech just put googly eyes on an algorithm" 😀
(edited for typo)
Release v2.4.10 of Ktistec
I'm trying to get through the backlog of bugs and features in my to-do list. Release v2.4.10 of Ktistec packages up several important improvements. The most impactful change is graceful server shutdown—I've never had a problem with shutdown leaving the database in a broken state, but prevention is the best cure.
Added
- Support manually refreshing actor information. (fixes #112)
- Add link to log level settings to the navigation bar.
Fixed
- Enable dragging source links to the address bar. (fixes #109)
- Fix missing reply/mention notifications for non-create activities.
- Ensure the network is up before attempting to refresh a page.
Changed
- Block actor handle and display name when actor or post is blocked.
- Gracefully shut down the server.
I'm considering adding lightweight multi-user support (invitation-only, not open registration). I'm interested in your thoughts on whether this would be useful.