Old man tries things, Nano Banana edition
In which I use models to go back to the past
-
-
Writing an agentic conversational game - II
In which I use agents to write an agent-based game
-
Writing an agentic conversational game - I
In which I use agents to write an agent-based game
-
Reinforcement Learning II - Basic algorithms
In which I take baby steps towards RL
-
Running a multimodal embedding model for image classification
In which I vibe-code something at work
-
Reinforcement Learning I - Connect 4
In which I vibe code a Connect 4 game
-
Local LLMs V - Installing and running vLLM
In which I go the easy way
-
Adding Codex and Claude Code notifications to Alacritty
In which I try to know what the agents are up to
-
Vibe coding for senior software engineers
In which I have to, once more, learn how to code
-
Clair Obscure: Expedition 33
In which I get hooked on a game
-
Local LLMs IV - Installing and running TensorRT-LLM
In which I try to go the NVIDIA way
-
Reinstalling Ubuntu
In which I go down from Ubuntu 25.04 to Ubuntu 24.04
-
Local LLMs III - Installing and running llama.cpp
In which I try to ride a llama
-
Redesigning the blog
In which I use Codex to fake my way into web design
-
Local LLMs II - Requirements to run a local LLM
In which I try to figure out what I need to run an LLM on my computer
-
Local LLMs I - Setting up a home computer
In which I try to make my NVIDIA drivers work