Posts

This is a follow-up post to my experiments with local models for code optimization. In the previous post, I give more background on how and why the experiment was set up. I mention some limitations of the approach. And some things which, in retrospect, I would do differently. Nevertheless, only two things changed in this experiment: the models, and where inference ran. I picked three frontier models, and three large open-weight models. The inference ran in the cloud, via OpenRouter. ...

During his keynote at ACCU on Sea in June, Andrei Alexandrescu made some predictions. One of those was the integration of LLMs and compilers. Compilers can generate optimization remarks for LLMs to process. And LLMs can propose optimizations that are difficult for a conventional compiler to discover. If you haven’t yet, I very much recommend you to watch Andrei’s talk. It’s a great talk, and it led me down a rabbit hole of experimenting: what could an LLM do today? Integrated into the compiler pipeline, locally on my hardware? ...

I work a lot on remote servers using SSH. Emacs makes it easy to open files from within an SSH session and have them appear on your local desktop. But you might prefer another editor, or perhaps you need to open a file that Emacs does not support. I created remote-open: a Python script that provides a similar workflow while letting you choose which applications open the files. More on that further down. First, a little demo. Then I’ll explain the Emacs setup. If you want to skip Emacs, you can scroll down to the section about remote-open. ...

We are nearing the end of the Hugging Face Build Small Hackathon. Time to write about my experiences: why I built Chorus, how I built it, and what I would change given more time. The plan A few months ago, I heard WSJ columnist Louise Perry on her podcast wishing she had a trusted assistant who could read her social media comments. These comments can contain valuable feedback, but they also contain abuse and personal attacks. ...