AI engineering glossary · LLM training alignment
What is debate (AI safety)?
Debate (AI safety) (also called AI safety via debate): A proposed oversight method in which two AI systems argue opposite sides of a question and a human judge decides who is more convincing, on the idea that it is easier to judge arguments than to solve hard problems directly.
Debate (AI safety): an example
Two models argue whether a code change is safe; each points to lines that support its claim, and the judge picks a winner.
Related terms
More LLM training alignment terms
- DeepSpeed
- Direct preference optimisation
- Domain-adaptive pretraining
- DoRA
- Double quantisation
- Emergent abilities
- Evol-Instruct
- Exposure bias
Where you learn it
Debate (AI safety) is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.