Adversarial examples - a vulnerability of every AI model, and a “mystery” of deep learning - may simply come from models cramming many features into the same neurons! Less feature interference → more robust models. New research from @livgorton 🧵 (1/4)

🚨 New paper alert! 🚨 Are human baselines rigorous enough to support claims about "superhuman" performance? Spoiler alert: often not! @prpaskov and I will be presenting our spotlight paper at ICML next week on the state of human baselines + how to improve them!