Results for "goal divergence"

AdvertisementAd space — search-top

54 results

Next-Token Prediction Intermediate

Training objective where the model predicts the next token given previous tokens (causal modeling).

Foundations & Theory
Active Learning Intermediate

Selecting the most informative samples to label (e.g., uncertainty sampling) to reduce labeling cost.

Foundations & Theory
Quantization Intermediate

Reducing numeric precision of weights/activations to speed inference and reduce memory with acceptable accuracy loss.

Foundations & Theory
Model Stealing Intermediate

Reconstructing a model or its capabilities via API queries or leaked artifacts.

Foundations & Theory
Planner-Executor Intermediate

Separates planning from execution in agent architectures.

AI Economics & Strategy
Conditional Random Field Intermediate

Probabilistic graphical model for structured prediction.

Model Architectures
3D Reconstruction Intermediate

Recovering 3D structure from images.

Computer Vision
Hierarchical Planning Advanced

Decomposing goals into sub-tasks.

Agents & Autonomy
Wake Word Detection Intermediate

Detects trigger phrases in audio streams.

Speech & Audio AI
Deliberative Agent Advanced

Agent reasoning about future outcomes.

Agents & Autonomy
Blackboard System Advanced

Agents communicate via shared state.

Agents & Autonomy
Reward Hacking Advanced

Maximizing reward without fulfilling real goal.

AI Safety & Alignment
Likelihood Function Advanced

Probability of data given parameters.

Probability & Statistics
Outer Alignment Advanced

Correctly specifying goals.

AI Safety & Alignment
Self-Consistency Intro

Sampling multiple outputs and selecting consensus.

Prompting & Instructions
Transparency Obligation Intermediate

Requirement to inform users about AI use.

Governance & Ethics
Plant Intermediate

The physical system being controlled.

Foundations & Theory
Inverse Reinforcement Learning Advanced

Inferring reward function from observed behavior.

Reinforcement Learning
Motion Planning Advanced

Computing collision-free trajectories.

Motion Planning & Navigation
Pareto Optimality Advanced

No agent can improve without hurting another.

Agents & Autonomy
Surrogate Model Advanced

Fast approximation of costly simulations.

AI in Science
Tripwire Advanced

Signals indicating dangerous behavior.

AI Safety & Alignment
Compute Governance Intermediate

Regulating access to large-scale compute.

Governance & Ethics
State Estimation Advanced

Inferring the agent’s internal state from noisy sensor data.

Robotics & Embodied AI

Welcome to AI Glossary

The free, self-building AI dictionary. Help us keep it free—click an ad once in a while!

Search

Type any question or keyword into the search bar at the top.

Browse

Tap a letter in the A–Z bar to browse terms alphabetically, or filter by domain, industry, or difficulty level.

3D WordGraph

Fly around the interactive 3D graph to explore how AI concepts connect. Click any word to read its full definition.