A new essay arguing that neural networks are far more readable than assumed — with about 90 percent of neurons serving identifiable purposes — has divided AI safety researchers, who see both promise and risk in the claim.
AI Interpretability Debate Intensifies Over Claim That 90 Percent of Neurons Have Clear Functions
A new essay arguing that neural networks are far more readable than assumed — with about 90 percent of neurons serving identifiable purposes — has divided AI safety researchers, who see both promise and risk in the claim.
Monitoring item. The full text is not distributed. Extract and source below.