Learn to use AI
Does it work?
Does it work? is a unit of 8 lessons in Rabbithole's Learn to use AI course, at level 2.
Lessons
- Benchmarks: how AI models get testedLevel 2
- Evaluation: how you tell whether an AI is any goodLevel 2
- Testing an AI agent: what evals are and why to start earlyLevel 2
- NLP tasks: the jobs we give language modelsLevel 2
- How AI reasoning is testedLevel 2
- Robustness evaluation: does the AI hold up when things change?Level 2
- Selection Bias in BenchmarksLevel 2
- Contamination: when a model has already seen the testLevel 2
Sources
These lessons draw on 21 sources. The most used:
- Holistic Evaluation of Language Models
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
- System Card: Claude Opus 4.6
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Demystifying evals for AI agents
- ARC-AGI
- Claude Docs — Test and Evaluate