Stefan Munz – OnTree.co
@stefanmunz.bsky.social
Founder of OnTree.co. Helping you own your AI and escape the sticky, overpriced SaaS trap. Join the movement 🐣
Köln, I am coming! Looking forward to meet a lot of new people at the Digitale Leute Summit tomorrow. Super happy to be part of their trainer team for their upcoming AI Software Engineering Bootcamp mext year!
www.digitale-leute.de/summit/25/
www.digitale-leute.de/summit/25/
November 12, 2025 at 12:55 PM
Köln, I am coming! Looking forward to meet a lot of new people at the Digitale Leute Summit tomorrow. Super happy to be part of their trainer team for their upcoming AI Software Engineering Bootcamp mext year!
www.digitale-leute.de/summit/25/
www.digitale-leute.de/summit/25/
Great to see Charity Majors live on stage finally, I‘m a huge fan! In praise of normal engineers, the perfect topic at this time!
November 5, 2025 at 11:44 AM
Great to see Charity Majors live on stage finally, I‘m a huge fan! In praise of normal engineers, the perfect topic at this time!
Cutest moment with Claude Code this week: Trying to find out how much power this home server draws, only to find out Claude is the top consumer right now. "That's me!"
October 10, 2025 at 1:17 PM
Cutest moment with Claude Code this week: Trying to find out how much power this home server draws, only to find out Claude is the top consumer right now. "That's me!"
💪 Finally, it works. This took longer than expected. The infrastructure for self updates with Go is awesome. It is still a hassle to implement, unfortunately. Now it works, two production systems up and running. Fingers crossed no agent breaks this code tomorrow...
October 9, 2025 at 9:54 AM
💪 Finally, it works. This took longer than expected. The infrastructure for self updates with Go is awesome. It is still a hassle to implement, unfortunately. Now it works, two production systems up and running. Fingers crossed no agent breaks this code tomorrow...
Current Status: Comparing 4 reviews from LLMs for my newest newsletter article, coming out tomorrow. I keep coming back to Gemini 2.5. Pro for these tasks. Claude and ChatGPT answers often feel rushed, as if they didn't really take the time to read the piece. Sloppy somehow. New in the mix is ...
October 8, 2025 at 9:23 AM
Current Status: Comparing 4 reviews from LLMs for my newest newsletter article, coming out tomorrow. I keep coming back to Gemini 2.5. Pro for these tasks. Claude and ChatGPT answers often feel rushed, as if they didn't really take the time to read the piece. Sloppy somehow. New in the mix is ...
Claude realizing by itself that this is getting too messy. I'd like to see more of that!
October 2, 2025 at 3:26 PM
Claude realizing by itself that this is getting too messy. I'd like to see more of that!
Finally my Framework Desktop machine has shipped, can't wait for it! frame.work/de/en/desktop
September 27, 2025 at 8:40 AM
Finally my Framework Desktop machine has shipped, can't wait for it! frame.work/de/en/desktop
Game Over for the week, at least with Codex. Surprisingly good value for 20 dollars per month, highly recommended! Not as addictive as Claude Code, but in a good way.
September 26, 2025 at 12:32 PM
Game Over for the week, at least with Codex. Surprisingly good value for 20 dollars per month, highly recommended! Not as addictive as Claude Code, but in a good way.
Recently, I've defaulted to using my coding agents in YOLO mode. I found a better way to balance security and ease of use. Read the full article with links here: www.stefanmunz.com/posts/2025/a...
September 25, 2025 at 6:36 AM
Recently, I've defaulted to using my coding agents in YOLO mode. I found a better way to balance security and ease of use. Read the full article with links here: www.stefanmunz.com/posts/2025/a...
Claude Code is overloaded at 9:30 A.M.? Usually that's the best time, because America is still sleeping. Is Europe finally waking up?
September 24, 2025 at 7:40 AM
Claude Code is overloaded at 9:30 A.M.? Usually that's the best time, because America is still sleeping. Is Europe finally waking up?
Full house at the Agentic Coding Meetup Hamburg #2
September 23, 2025 at 4:49 PM
Full house at the Agentic Coding Meetup Hamburg #2
Happy to report that the AMD Strix Halo (AI 395+) computers support quite large mixture-of-experts models like Llama 4 Scout. With a respectable response rate of 15 to 16 token/sec. We're getting closer to letting you own your AI. 💪
July 24, 2025 at 2:10 PM
Happy to report that the AMD Strix Halo (AI 395+) computers support quite large mixture-of-experts models like Llama 4 Scout. With a respectable response rate of 15 to 16 token/sec. We're getting closer to letting you own your AI. 💪
Sitting in a café and making my homeserver pull another model. It's nice seeing it all coming together slowly.
July 24, 2025 at 2:06 PM
Sitting in a café and making my homeserver pull another model. It's nice seeing it all coming together slowly.
Boris Cherny liked one of my posts on Threads, this week is exceptionally good!
July 17, 2025 at 11:41 AM
Boris Cherny liked one of my posts on Threads, this week is exceptionally good!
Over two hours, this was the longest run so far. Telling Claude Code to fix unit and lint tests after each ticket seems to cause longer runs. Let's see if it also means better quality.
July 17, 2025 at 11:38 AM
Over two hours, this was the longest run so far. Telling Claude Code to fix unit and lint tests after each ticket seems to cause longer runs. Let's see if it also means better quality.
Thanks to @steipete.me for publishing his epic 3 hour video, that got me started! And thanks to @mitsuhiko.at for sharing his experiences with Go and LLMs. It's the best language for agentic coding, at least for web apps. And all this written while Claude executes with project-manager
July 17, 2025 at 9:27 AM
Thanks to @steipete.me for publishing his epic 3 hour video, that got me started! And thanks to @mitsuhiko.at for sharing his experiences with Go and LLMs. It's the best language for agentic coding, at least for web apps. And all this written while Claude executes with project-manager
Really excited for my lightning talk tomorrow at the Agentic Coding Meetup Hamburg! Just finished my slides, if you want to know why it's two vacuum robots dueling in the image, you better join tomorrow!
July 14, 2025 at 11:32 AM
Really excited for my lightning talk tomorrow at the Agentic Coding Meetup Hamburg! Just finished my slides, if you want to know why it's two vacuum robots dueling in the image, you better join tomorrow!
Haha, apparently this is too boring work Claude. Now he blames the failing tests on another change. Which he of course cannot be held accountable for. This thing behaves more and more like a real developer...
July 1, 2025 at 2:43 PM
Haha, apparently this is too boring work Claude. Now he blames the failing tests on another change. Which he of course cannot be held accountable for. This thing behaves more and more like a real developer...
Call me lazy, but asking Claude to not only run the tests locally but also on GitHub Actions is so convenient
July 1, 2025 at 1:52 PM
Call me lazy, but asking Claude to not only run the tests locally but also on GitHub Actions is so convenient
I thought I had left daily system restarts behind when I stopped using XCode... 😂
June 24, 2025 at 7:02 AM
I thought I had left daily system restarts behind when I stopped using XCode... 😂