It talks about the origins of Mechanistic Interpretability as a term, a field and a community... and some drama.. :P
paper link: arxiv.org/abs/2410.09087
blogpost link: shreyansjainn.github.io/blog/2026/me...
This year, I'm trying to get over the fear of writing and publishing, because I always thought, what unique thing can I publish? So I stopped thinking that and thought, why not just publish notes of a paper I'm reading, so here it is...
starting with a paper called Mechanistic?
Microsoft Research NYC is hiring a researcher in the space of AI and society!
got inspired by a twt article and blabbered my thoughts on being a "lazy ambitious" person cause it was a hard relate!!!
the quickest thing i’ve written till date, from thought to publish took 30 mins… 😅
shreyansjainn.github.io/blog/2026/la...
We’re bringing back a Community Spotlight talk series, highlighting cool work being done by members of our community. We’re kicking it off with a talk on running diffusion-based world-models in real time on consumer hardware.
Jan 9th at 2 pm US Eastern Time
any recommendations on which interpretability researchers to follow here, people who are pretty active here?
Just once in my life I want to experience Russell Westbrook-level confidence. Can you imagine how incredible it must feel.
