**Uwe L. Korn**, Data Scientist, Music Hacker and Food lover.
On Thursday morning, I was excited to see the release of Inkling-Small. Last week brought us Laguna-S-2.1 which is a pretty good coding model given that it fits onto a 128GB RAM MacBook Pro. Sadly, Laguna-S-2.1 has the downside of overthinking, especially when it isn’t a purely agentic coding task. This was already visible in the automatic, local code reviews I do with roborev.
Just two days ago, I published my current workflow with the feeling that in some weeks I can probably share the next update. Today, it seems that Poolside shipped a model that already introduces some change. They have released Laguna-S-2.1, a 118B total parameter Mixture-of-Experts (MoE) model with 8B activated parameters per token. It supports up to 1M tokens in context. I was excited to see in…
My journey to optimise my agentic coding setup has now led me to consider running an LLM locally and removing all permission prompts. Even though I don’t check every action of the agent anymore, I feel much more in control of what they are doing. My setup is now comprised of pi as my main coding agent, a sophisticated sandbox setup, some helpful tools and a wide mix of LLMs.
In the last two months, I wanted to get people to experiment more with agentic coding tools. While I have seen successful uses of them, some people still weren’t using them at all, and others stuck with one tool (mostly GitHub Copilot) and assumed that all other tools were similar. Given the changes we are currently observing in the software engineering space, the level of experimentation I was…
AI summaries mean that you need to click less on search results to find the actual information you’re looking for. But for me, as someone who writes a lot of deep tech in blog posts, I have seen that it’s still worth it to write the blog post, and it’s still worth it for the readers you want to read your articles to actually read those blog posts and get there with AI. You won’t reach millions,…
Personally, I was keen to ensure that Python 3.14 availability on conda-forge was as good as possible on the actual release day. conda-forge’s build infrastructure is a massive benefit, and I wanted to show others how this can result in useful progress for them.
In recent times, it has become common for people to post about how they’re becoming more efficient with the use of AI. I want to follow that trend and also provide a quick overview of where I’ve been using AI in my workflow over the last months to ensure I’m as efficient as possible. Some of the gains have been in place for months; some of the things I’m using are actually ones I discovered in the…
As I was intrigued by @hugovk’s BlueSky post on usable Python 3.14 packages on PyPI, I wanted to see how the situation is on conda-forge. Here, we have a different setup where central tooling pushes even more towards availability.
During the last five weeks (2025-37, 2025-38, 2025-39, 2025-40, and 2025-41) I logged my conda-forge activity as a blog post. Instead of only reporting on it, I also wanted to have a look at what I have been doing there and whether things could be automated more.
This week was the Python 3.14 release, and it will also be the final week where I log my conda-forge work. While it is interesting for me to see what I do work, it is also additional work that keeps me from contributing to conda-forge itself. Still, as a follow-up, I will write at least one more post that reviews the kind of work I have done in the last weeks and how that could be made more…