2 Comments
User's avatar
Daniel Popescu / ⧉ Pluralisk's avatar

Excellent analysis, you articulate the black box issue perfectly. Given the 'trillions of parameters' and the rise of 'Agentic' software, how do you see mechanistic interpretability scaling efectively?

Expand full comment
Alde's avatar

I think we need more investment in the space so researches can try new interpretability methods.

I think we are in the right path but we need a boost, more awareness and ultimately more experiments.

The bridge between investment in AI infra and applications compare to AI Safety is way too large.

Expand full comment