Uploaded October 2026 | Updated November 2026, 8 hours ago
AI progress looks like sudden jumps from the outside. From the inside, it's a smooth line that crosses a threshold.
Emmanuel Ameisen, Interpretability Researcher at Anthropic, on why 80% accuracy is useless, 99% is useful, and the model that got Claude writing most of his code.
AI progress looks like sudden jumps from the outside. From the inside, it's a smooth line that crosses a threshold.
Emmanuel Ameisen, Interpretability Researcher at Anthropic, on why 80% accuracy is useless, 99% is useful, and the model that got Claude writing most of his code.










