Reinforcement Learning
Training by trial, error and reward rather than by examples. It is how models are tuned to be helpful and to refuse things they should refuse.
Related terms
User-Agent
The name a browser or bot gives when it requests a page. It is how a server tells Googlebot from ChatGPT from a person, and how robots.txt rules are addressed to one and not another.
AI Citation
When an assistant names your website as the source of something it said, usually with a link. A citation is the AI-era equivalent of a first-page ranking — it is the thing worth competing for.
Grounding
Giving an AI real source material to answer from, instead of letting it rely on memory. A grounded answer can be checked and cited; an ungrounded one is where hallucinations come from.
Generative AI
AI that produces something new — text, images, code, audio — rather than only classifying or predicting. The generative part is why it can write an answer about your business instead of just linking to it.
Hallucination
When an AI states something false with complete confidence — an invented price, a policy you never had, a product you do not sell. The usual cause is that the correct fact was not available anywhere it could read.
Content Negotiation
When the same URL serves different formats depending on what the visitor asks for — HTML for a browser, Markdown for an assistant. It lets one address serve people and machines without either getting a compromise.