Tag: scaling

• Data or architecture: the control experiment nobody runsAug 14, 2026

  Before AlexNet the field's best argument against neural networks was that the data was doing the lifting — and Efros had the control experiment to prove it. AlexNet settled that case on the same data everyone else had. The reason to keep the episode is that the modern version of the argument is running now, with the control missing.

  deep-learning-historyscalingevaluationagentic-engineering
• Reading notes: Sutskever's List (Heimann), ch. 1–2Aug 14, 2026

  Richard Heimann's book reads the reconstructed reading list Ilya Sutskever gave John Carmack as an argument rather than a bibliography. Chapters 1 and 2 give the four-part worldview it claims to encode, and then spend a chapter showing that AlexNet invented almost nothing — which is the part this notebook cares about.

  reading-notesdeep-learning-historyscaling