interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came
some of the best times in college was when we got to hear stories about computers and the internet from when we were infants🐣🍼
@SJoyMountford will be sharing her stories from starting and leading the first human interface group at apple in the 90s today at 6pm pst
link below
