Learn to use AI
Can you trust it?
Can you trust it? is a unit of 5 lessons in Rabbithole's Learn to use AI course, at levels 1 to 2. 4 of these lessons are also in Become an AI engineer as “Truthfulness, plainly”.
Lessons
- Hallucination: when AI sounds sure but is wrongLevel 1
- Is the answer true? Truthfulness and factualityLevel 2
- Sycophancy: when an AI just tells you what you want to hearLevel 2
- Calibration: does the AI's sureness match reality?Level 2
- Sandbagging: when an AI holds back on a testLevel 2
Sources
These lessons draw on 19 sources. The most used:
- AI Security Institute
- Why Language Models Hallucinate
- International AI Safety Report 2026
- Survey of Hallucination in Natural Language Generation
- Language Models (Mostly) Know What They Know
- Teaching Models to Express Their Uncertainty in Words
- TruthfulQA: Measuring How Models Mimic Human Falsehoods
- Why language models hallucinate