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

1. Hallucination: when AI sounds sure but is wrong · Level 1
2. Is the answer true? Truthfulness and factuality · Level 2
3. Sycophancy: when an AI just tells you what you want to hear · Level 2
4. Calibration: does the AI's sureness match reality? · Level 2
5. Sandbagging: when an AI holds back on a test · Level 2

## Sources

These lessons draw on 19 sources. The most used:

- [AI Security Institute](https://www.aisi.gov.uk/)
- [Why Language Models Hallucinate](https://arxiv.org/abs/2509.04664)
- [International AI Safety Report 2026](https://internationalaisafetyreport.org/sites/default/files/2026-02/international-ai-safety-report-2026.pdf)
- [Survey of Hallucination in Natural Language Generation](https://arxiv.org/abs/2202.03629)
- [Language Models (Mostly) Know What They Know](https://arxiv.org/abs/2207.05221)
- [Teaching Models to Express Their Uncertainty in Words](https://arxiv.org/abs/2205.14334)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://arxiv.org/abs/2109.07958)
- [Why language models hallucinate](https://openai.com/index/why-language-models-hallucinate/)

[All units in Learn to use AI](https://rabbithole.pro/courses/learn-ai)

Source page: https://rabbithole.pro/courses/learn-ai/can-you-trust-it