Sckathach’s post

It’s still under construction, as I’m waiting to learn more about Manim before decorating it :eyes:. But you can already check out:

• 18/03/25 - Subspace Rerouting: Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models Post / Webpage

• 28/08/25 - Combining TAP and DSPy to generate quick and efficient jailbreaks Post

• 15/09/25 - Exploring the multi-dimensional refusal subspace in reasoning models Post