EDUCATION
3 items
3 posts
Blog
TutorMoments: AI2's New Benchmark Shows LLM Tutors Over-Help by DefaultTutorMoments, AI2's replay-based benchmark for LLM tutors, finds models over-help by default. How it scores scaffolding and rigor in real tutoring transcripts.
Blog
AI Tutor Shows 0.71-1.30 SD Effect Size in Dartmouth Statistics CourseA Dartmouth study of an AI tutor in intro statistics links full engagement to a 0.71-1.30 SD exam gain. What it measured, and why selection bias still matters.
Blog
A Free Compilers Textbook That Actually Teaches You to Build OneDouglas Thain's free compilers textbook walks you through building a C-like compiler that emits real X86 and ARM assembly, plus what HN recommends reading next.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever