*a site where daniel makes short, frequent posts.
Everyone is an analyst*
*= They feel like one. No in the day and age of AI everyone that is using one feels like they need access to data to “analyse” the data. Why not have on person do that?
Grok Bot for Home Assistant with their MCP
A week ago I started using Grok Bot for some hobby projects and found out that there’s a Home Assistant MCP from the Open Source community. And wow: It’s great! Read moreSo, Ministral tried to generate SQLAfter connecting it to Grok Bot I asked it a few simple questions: What lights do I have? And…
Watermarking AI output helps AI Companies
I fully understand why AI companies comply with the EU to watermark AI-generated content. This makes it a lot easier for them to train on human-made content, since it’s watermarked. It reminds me of this study, where if you put images of the health effects of smoking on cig. packages, people actually smoke more. Of…
Avoid LuxFlat in Luxembourg
Their apartments are not cleaned properly, contain bed bugs and their service is basically non-existent. We tried reaching out for service, but that’s a no-go. They don’t reply, nor do they offer any compensations/refunds. STAY FAR AWAY FROM THEM!
Code was carved in stone, it now is clay but will become water.
The title says it all. Before the era of agentic-programming software had to be designed so it could be not touched for a very long time. It was carved in stone. With the speed you can build, update and maintain features nowadays (and not even talking about parallel agents working on things) things have started…
Passion in the Age of AI
A quick note before we start. I wrote this by hand, based on a voice note I recorded while driving home from a colleague. I used AI — Opus 4.8 on extra-high thinking — to help me ideate, fix my grammar, and shape it here and there. But it has been fully read, approved, and…
Claude’s voice mode is awesome!
Since the release of GPT’s proper voice mode, where it sighs and such, I’ve been using voice agents for ideating and learning more. Recently, Anthropic updated Claude’s own voice mode and I think it’s powered by ElevenLabs their voice models (just an assumption based on how it sounds) and I have to say: I’m impressed.…
Properly* setting up Immich on an Arm-Based UGREEN NAS which can use the NPU!
A note in advance: This is tested on the ARM variants of the UGREEN Nas. I currently have the UGREEN DH4300 Plus and I assume this works on the two bay variant as well which is the UGREEN NASync DH2300. *= There are probably loads of other things you can tweak, but this helps with…
OpenClaw doesn’t feel like it’s for me yet
For the past few days, I’ve been playing with OpenClaw (Formerly Moltbot, formerly Clawdbot) and it’s kinda been a bummer. The UI of the admin is one big mess/chaos, of course it’s all vibe coded but I vibe code some projects too and I invest a lot of time in making the experience of how…
MiniMax M2.1 still beats Kimi K2.5
Even if Kimi is better on BenchMarks, MiniMax seems to be a lot better in backend code in the wild. Our codebase is well over 500k lines of code and MiniMax seems to navigate it a lot better than Kimi. And you can clearly see that on the statistics of Kilo, that people like MiniMax’s…
Backend Git Bisect with an Agent
Today I committed a few “wip” commits and during one of those commits I broke some code and caused tests to fail. I got curious and wanted to see if an LLM could git bisect and the answer was: yes, very fast! The LLM (Gemini 3 Flash in this case) quickly started the bisect and…
Qwen’s response to Grok Code 1 Fast?
Grok Code 1 Fast has been a smash hit since it’s launch, mainly because it was a free model with a peak of 240B tokens on one day: This is the only thing I can think about when I read the new model’s information of Qwen3 Coder Next: that it’s a competitor to Grok’s coding…
