Results for "intelligence grounding"
Constraining outputs to retrieved or provided sources, often with citation, to improve factual reliability.
Model-generated content that is fluent but unsupported by evidence or incorrect; mitigated by grounding and verification.
Architecture that retrieves relevant documents (e.g., from a vector DB) and conditions generation on them to reduce hallucinations.
Prompt augmented with retrieved documents.
Distributed agents producing emergent intelligence.
Intelligence and goals are independent.
The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, planning, and decision-making—via algori...
AI capable of performing most intellectual tasks humans can.
Rate at which AI capabilities improve.
Sudden jump to superintelligence.
System-level design for general intelligence.
System that independently pursues goals over time.
Artificial environment for training/testing agents.
Intelligence emerges from interaction with the physical world.
Collective behavior without central control.
AI limited to specific domains.
A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience rather than explicit rule-coding.
Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.
A high-capacity language model trained on massive corpora, exhibiting broad generalization and emergent behaviors.
A discipline ensuring AI systems are fair, safe, transparent, privacy-preserving, and accountable throughout lifecycle.
A hidden variable influences both cause and effect, biasing naive estimates of causal impact.
AI focused on interpreting images/video: classification, detection, segmentation, tracking, and 3D understanding.
AI subfield dealing with understanding and generating human language, including syntax, semantics, and pragmatics.
Categorizing AI applications by impact and regulatory risk.
A theoretical framework analyzing what classes of functions can be learned, how efficiently, and with what guarantees.
Required human review for high-risk decisions.
Central catalog of deployed and experimental models.
Logged record of model inputs, outputs, and decisions.
Legal or policy requirement to explain AI decisions.
Decomposing goals into sub-tasks.