Exploring How Reasoning Models Break Mechanistic Interpretability Techniques
Exploring How Reasoning Models Break Mechanistic Interpretability Techniques reveals several interesting facts.
- With the imminent release of OpenAI's -o3
- This is a talk I gave to my MATS 9.0 training scholars about the big picture of mech interp - as of Oct 2025, what had changed?
- A discussion on the philosophy of deep learning,
- Reasoning
- This talk was recorded at NDC AI in Oslo, Norway. #ndcai #ndcconferences #developer #softwaredeveloper Attend the next NDC ...
In-Depth Information on How Reasoning Models Break Mechanistic Interpretability Techniques
A talk I gave to my MATS 9.0 training program about Have you ever wondered what is actually going on inside the "mind" of a Large Language It's finally here: The public (and most complete) version of my talk covering every stage of the process to build Olmo 3 Think. Take your personal data back with Incogni! Use code WELCHLABS at the link below and get 60% off an annual plan: ...
Mechanistic Interpretability
Stay tuned for more updates related to How Reasoning Models Break Mechanistic Interpretability Techniques.
