RLHF (Reinforcement Learning from Human Feedback)
A fine-tuning method where humans rate the quality of a model's responses, and the model is adjusted to more often produce answers that humans rate highly. It's a key step in making an AI model helpful and safe, not just technically functional.
See also
Embedding
A numeric representation of text, an image, or another object as a vector, where semantic similarity between objects is reflected in the closeness of their vectors. It's used to find similar documents and underlies RAG and vector databases.
AI Agent
An LLM-based system that can not only answer questions but also independently plan steps, call external tools (search, code, APIs), and carry out multi-step tasks to reach a goal with minimal human involvement.
Multimodal AI
A model that can understand and/or generate multiple types of data at once — text, images, audio, and video — rather than just text. For example, it can analyze a photo and answer a question about it in text.
Diffusion Model
A type of generative model that learns to create images (or other content) by gradually "cleaning up" random noise until a coherent picture emerges. It underlies most image generators, including Midjourney, Stable Diffusion, and DALL-E.
Foundation Model
A large model trained on a broad dataset that serves as the base for many narrower applications through fine-tuning or prompting — instead of training a separate model from scratch for every task.
Chain-of-Thought
A technique where the model "thinks out loud" step by step before giving its final answer, instead of producing a result immediately. It noticeably improves accuracy on tasks that require logic or math.