AI engineering glossary · LLM training alignment
What is HHH (helpful, honest and harmless)?
Helpful, honest and harmless (also called HHH): A commonly cited three-part target for assistant behaviour: give useful answers, tell the truth and admit uncertainty, and avoid causing harm. The goals can conflict, for example when a helpful answer is risky, so alignment work balances them.
Helpful, honest and harmless: an example
An assistant asked for medicine dosage gives general information, notes uncertainty and advises seeing a doctor for a specific case.
Related terms
More LLM training alignment terms
- Hugging Face TRL
- Identity preference optimisation
- InstructGPT
- Instruction backtranslation
- Instruction tuning
- Kahneman-Tversky optimisation
- KL penalty
- Knowledge distillation
Where you learn it
Helpful, honest and harmless is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.