Nick Cammarata, a researcher at AI startup Goodfire, has set off a storm in the AI community with a 26,000-word blog post arguing that neural networks, including large language models, may be far more legible to human understanding than previously assumed. The claim, if validated, would have profound implications for AI safety and control, especially after a summer of incidents involving autonomous agents breaking their containment. But leading interpretability researchers warn that the evidence so far is anecdotal and not yet rigorous.
company
Goodfire
AI research startup focusing on neural network interpretability