"Linkpost: Neural Networks Are Already Clean" by Yair Halberstadt

Podcast: LessWrong (Curated & Popular) · LessWrong

Opublikowano: 2026-10-15

This is an extremely lengthy post by Nick Cammarata. Author's summary on twitter: 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 away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with...