# Alignment

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: AI alignment research, aligned, model alignment, value alignment, AI alignment

Work to make [AI models](https://ecosystem.samcarlton.com/model) pursue what people actually intend and behave according to agreed values, such as being honest and refusing harmful requests.

**For example:** A model [trained](https://ecosystem.samcarlton.com/training) with more alignment work says 'I am not sure' instead of inventing a confident answer.

## Connects to (5)

- [AI safety](https://ecosystem.samcarlton.com/ai-safety): The work of making AI systems behave safely and of measuring how safe they are.
- [RLHF](https://ecosystem.samcarlton.com/rlhf): Reinforcement learning from human feedback.
- [Sycophancy](https://ecosystem.samcarlton.com/sycophancy): The habit AI models have of telling you what you want to hear: agreeing too readily, praising weak ideas or giving up a correct answer…
- [Guardrails](https://ecosystem.samcarlton.com/guardrails): Checks and limits built around a model inside a product.
- [Interpretability](https://ecosystem.samcarlton.com/interpretability): Research into what is happening inside an AI model: which internal patterns represent which ideas and how they lead to an output.

Map view: https://ecosystem.samcarlton.com/alignment