Training
RLHF
Reinforcement Learning from Human Feedback — the training technique that teaches AI models to be helpful, harmless, and honest.
01 ——
In plain English
RLHF (Reinforcement Learning from Human Feedback) is the process used to align a language model's outputs with what humans actually find helpful and safe. It's the main technique behind why ChatGPT, Claude, and similar assistants feel more useful and less erratic than raw pre-trained models.
How it works (simplified):
- The base model generates many responses to the same prompt
- Human raters rank those responses from best to worst
- A "reward model" is trained to predict human preferences
- The base model is further trained to maximise that reward score
Why it matters: Without RLHF, LLMs often produce text that is technically plausible but unhelpful, offensive, or unsafe. RLHF is what turns a raw language model into a usable assistant.
02 ——
Related terms
LLM
Large Language Model — the type of AI behind tools like ChatGPT and Claude, trained to understand and generate text.
Fine-tuning
Further training a pre-trained AI model on your own data to specialise it for a specific task or style.
Alignment
The challenge of making AI systems behave in ways that match human values and intentions — not just their literal instructions.
Guardrails
Rules and filters that constrain what an AI model can output — used to block harmful, off-topic, or non-compliant responses.
Training Data
The dataset an AI model learns from — its quality, diversity, and biases directly shape what the model can do and how well it does it.
Back to glossaryLast reviewed May 2026