AI
Computer systems that perform tasks normally needing human intelligence, such as understanding language, recognising images or making predictions.
In more detail
Most AI products today are built on machine learning models trained on data rather than on hand-written rules. Generative AI, which writes text, code, images or audio, is the branch that large language models belong to. Because these systems learn from examples, their output varies and can be wrong, so applications built on them need checks around them.
Example
Streaming Route Handlers send AI answers to the browser as they are generated.Related terms
- token (language model) — The unit of text a language model reads and writes: a word, part of a word, a punctuation mark or a byte sequence from the tokenizer's vocabulary.
- Server-Sent Events — A standard way for a server to keep an HTTP response open and push a stream of text events to the client, in one direction only.
Taught in
- A Project Nobody Owns — Google Cloud Associate Cloud Engineer Exam Prep
- Two Hours, Sixty Questions — Google Cloud Associate Cloud Engineer Exam Prep
- Choosing Compute — Google Cloud Associate Cloud Engineer Exam Prep
- Data And Storage Products — Google Cloud Associate Cloud Engineer Exam Prep
- Networking: VPCs, Firewalls And Hybrid Links — Google Cloud Associate Cloud Engineer Exam Prep
- Tooling: Infrastructure As Code And AI Assistants — Google Cloud Associate Cloud Engineer Exam Prep
- Streaming Endpoints: Server-Sent Events & NDJSON Feeds — Next.js 15 & Modern App Router Architecture
- Keep Your Logger: The Logs Bridge And Log Records — OpenTelemetry Certified Associate (OTCA) Exam Prep