Tags¶
Browse wiki pages by topic tag.
agent¶
alignment¶
architecture¶
- Agent Architecture
- Context Management
- Context Rot
- Context Windows
- Defense in Depth
- Degradation and Recovery
- Delivery Modes
- Frontier vs Local Models
- Model Heterogeneity
- Multi-Agent Patterns
- RAG vs Fine-Tuning
- Reasoning Models and Extended Thinking
- Report 2: Multi-Agent Systems — Summary
- Retrieval-Augmented Generation
- Single-Agent vs Multi-Agent
- Statelessness
- Structured Output and Constrained Generation
- Tokenization
- Transformer Architecture
control-room¶
coordination¶
deployment¶
design¶
- HSI Architecture
- NUREG-0700 — Human-System Interface Design Review Guidelines
- Report 4: Operational Scenarios — Summary
emergency¶
- Emergency Response
- Scenario 5: Loss of Coolant Accident — Emergency Response
- Scenario 9: Compound Event with Ambiguous Indications
engineering¶
evaluation¶
failure-mode¶
- Calibration
- Context Divergence
- Hallucination
- Monoculture Collapse
- Output Vacuity (Slop)
- Prompt Injection and Adversarial Inputs
- Sycophancy
foundations¶
framework¶
fuel¶
hra¶
- ATHEANA
- HRA Methods Compared for AI-Assisted Operations
- Human Reliability Analysis
- IDHEAS-ECA
- NUREG-1792 — Good Practices for HRA
- NUREG-2199 — IDHEAS-ECA Methodology
- Performance Shaping Factors
- Report 5: Human Reliability Analysis — Summary
- SPAR-H
human-factors¶
- Automation Bias
- Cognitive Load and Agent Supervision Limits
- HSI Architecture
- Human Authority
- NUREG-0700 — Human-System Interface Design Review Guidelines
- NUREG-0711 — Human Factors Engineering Program Review Model
- Operator Modelling
- Report 3: Nuclear Regulatory & Human Factors — Summary
- Report 5: Human Reliability Analysis — Summary
- Situation Awareness
- Sycophancy
- Trust Calibration
implementation¶
independence¶
infrastructure¶
international¶
knowledge-grounding¶
llm¶
- Calibration
- Context Rot
- Context Windows
- Hallucination
- Non-Determinism
- Output Vacuity (Slop)
- Post-Training Alignment
- Reasoning Models and Extended Thinking
- Report 1: LLM Foundations — Summary
- Statelessness
- Structured Output and Constrained Generation
- Sycophancy
- Tokenization
- Transformer Architecture
local-deployment¶
memory¶
method¶
methodology¶
- Build vs. Assess Gap
- Capability Gradient
- NUREG-0711 — Human Factors Engineering Program Review Model
- NUREG-1792 — Good Practices for HRA
- NUREG-2199 — IDHEAS-ECA Methodology
microsoft¶
multi-agent¶
- AutoGen
- Cognitive Load and Agent Supervision Limits
- Common Cause Failure
- Context Divergence
- CrewAI
- Degradation and Recovery
- Delivery Modes
- Epistemic Independence
- LangGraph
- Model Heterogeneity
- Monoculture Collapse
- Multi-Agent Patterns
- Report 2: Multi-Agent Systems — Summary
- Single-Agent vs Multi-Agent
- Situation Awareness
nuclear¶
- 10 CFR 50 — NRC Regulations for Nuclear Power Plants
- Alarm Prioritization
- Automation Bias
- Build vs. Assess Gap
- Common Cause Failure
- Defense in Depth
- Electric Power Research Institute (EPRI)
- Emergency Response
- FRAPCON — Fuel Performance Simulation Code
- Graded Autonomy Tiers
- HSI Architecture
- Human Authority
- Human Reliability Analysis
- International Atomic Energy Agency (IAEA)
- Knowledge Graphs
- Local Deployment
- Non-Determinism
- PSA Integration
- Pressurised Water Reactor (PWR)
- Procedure-AI Interaction
- RELAP5 — Thermal-Hydraulic Simulation Code
- Report 1: LLM Foundations — Summary
- Report 2: Multi-Agent Systems — Summary
- Report 3: Nuclear Regulatory & Human Factors — Summary
- Report 4: Operational Scenarios — Summary
- Report 6: Prototyping Guide — Summary
- Shift Handover
- Simulator Coupling
- Small Modular Reactor (SMR)
- U.S. Nuclear Regulatory Commission (NRC)
operations¶
optimization¶
organization¶
- Electric Power Research Institute (EPRI)
- International Atomic Energy Agency (IAEA)
- U.S. Nuclear Regulatory Commission (NRC)
pattern-0¶
pattern-7¶
pattern-9¶
- Scenario 2: Developing RCS Temperature Anomaly
- Scenario 3: Concurrent Alarms During Reactor Transient
- Scenario 4: Independent Safety Verification
- Scenario 5: Loss of Coolant Accident — Emergency Response
- Scenario 6: Long-Term Fuel Integrity Monitoring
- Scenario 7: Instrument Channel Failure
- Scenario 8: Multi-Unit SMR Monitoring
- Scenario 9: Compound Event with Ambiguous Indications
protocol¶
prototyping¶
- Capability Gradient
- Evaluation Harness
- Operator Modelling
- Report 6: Prototyping Guide — Summary
- Simulator Coupling
psa¶
pwr¶
- Scenario 2: Developing RCS Temperature Anomaly
- Scenario 3: Concurrent Alarms During Reactor Transient
- Scenario 4: Independent Safety Verification
- Scenario 5: Loss of Coolant Accident — Emergency Response
- Scenario 7: Instrument Channel Failure
- Scenario 9: Compound Event with Ambiguous Indications
reactor¶
regulation¶
- 10 CFR 50 — NRC Regulations for Nuclear Power Plants
- Graded Autonomy Tiers
- International Atomic Energy Agency (IAEA)
- NUREG-0700 — Human-System Interface Design Review Guidelines
- NUREG-0711 — Human Factors Engineering Program Review Model
- NUREG-1792 — Good Practices for HRA
- NUREG-2199 — IDHEAS-ECA Methodology
- Report 3: Nuclear Regulatory & Human Factors — Summary
- U.S. Nuclear Regulatory Commission (NRC)
research¶
safety¶
- Automation Bias
- Calibration
- Cognitive Load and Agent Supervision Limits
- Common Cause Failure
- Context Management
- Context Rot
- Context Windows
- Defense in Depth
- Degradation and Recovery
- Emergency Response
- Epistemic Independence
- Graded Autonomy Tiers
- Hallucination
- Human Authority
- Knowledge Graphs
- Model Heterogeneity
- Monoculture Collapse
- Non-Determinism
- Output Vacuity (Slop)
- Post-Training Alignment
- Prompt Injection and Adversarial Inputs
- Reasoning Models and Extended Thinking
- Report 1: LLM Foundations — Summary
- Report 3: Nuclear Regulatory & Human Factors — Summary
- Situation Awareness
- Sycophancy
- Tool Calling
- Trust Calibration
safety-analysis¶
- HRA Methods Compared for AI-Assisted Operations
- Human Reliability Analysis
- PSA Integration
- Performance Shaping Factors
- Report 5: Human Reliability Analysis — Summary
scenario¶
- Scenario 1: Shift Handover Monitoring
- Scenario 2: Developing RCS Temperature Anomaly
- Scenario 3: Concurrent Alarms During Reactor Transient
- Scenario 4: Independent Safety Verification
- Scenario 5: Loss of Coolant Accident — Emergency Response
- Scenario 6: Long-Term Fuel Integrity Monitoring
- Scenario 7: Instrument Channel Failure
- Scenario 8: Multi-Unit SMR Monitoring
- Scenario 9: Compound Event with Ambiguous Indications
scenarios¶
security¶
simulation¶
- FRAPCON — Fuel Performance Simulation Code
- RELAP5 — Thermal-Hydraulic Simulation Code
- Simulator Coupling
smr¶
- Scenario 1: Shift Handover Monitoring
- Scenario 6: Long-Term Fuel Integrity Monitoring
- Scenario 8: Multi-Unit SMR Monitoring