Blog
AI Masterclass Blog
Explanations, background, and advice for curious students.
Topics
How machines learnSearch, planning, and probabilityNeural networks and computer visionLanguage models and transformersGames and reinforcement learningThe history of AI and AI in scienceInside the model: interpretability and alignmentStudying artificial intelligence
Latest articles

30 Jul 2026
Why a positive test for a rare disease is usually wrong
A test that is right 95 per cent of the time, a disease that 1 person in 100 has, and a positive result. The chance you have the disease is about 16 per cent. Here is the arithmetic on 1,000 people, and what a second test changes.

24 Jul 2026
What a gradient is and why every AI model follows one
Every model from a straight-line fit to a language model with hundreds of billions of parameters is trained by the same move: compute the slope of the loss and take a small step downhill. Three steps on a bowl, with every number, and the step that is too large.