Programmer.ie: Modern AI programming

Technical books for building with AI

Home
Books
Solutions
Learn
Prompts
Articles
Search
About

Deployment

Using Quantization to speed up and slim down your LLM

Recent Posts

Cellular Automata From First Principles 58: Capstone — Discover, Measure and Explain a New System
Cellular Automata From First Principles 57: Build a Cellular Automata Laboratory
Cellular Automata From First Principles 56: Generate Figures and Animations
Cellular Automata From First Principles 55: Run Parameter Sweeps and Benchmarks
Cellular Automata From First Principles 54: Make Experiments Reproducible
Cellular Automata From First Principles 53: Build a Reusable Cellular Automata Engine
Cellular Automata From First Principles 52: Use FFTs for Large Neighborhoods
Cellular Automata From First Principles 51: Run Cellular Automata on the GPU
Cellular Automata From First Principles 50: Vectorize the Update Loop
Cellular Automata From First Principles 49: Profile Before You Optimize
Cellular Automata From First Principles 48: What Did the Neural CA Actually Learn?
Cellular Automata From First Principles 47: Inspect Hidden-State Propagation
Cellular Automata From First Principles 43: Test Generalization Beyond Training
Cellular Automata From First Principles 46: Generalize to Harder and Larger Mazes
Cellular Automata From First Principles 42: Regenerate After Damage
Cellular Automata From First Principles 45: Learn to Solve Mazes
Cellular Automata From First Principles 41: Train for Persistence
Cellular Automata From First Principles 44: Neural Cellular Automata for Pathfinding
Cellular Automata From First Principles 40: Randomize the Update Schedule
Cellular Automata From First Principles 39: Grow a Target From One Seed
Cellular Automata From First Principles 38: Hidden Cell Channels and Local Memory
Cellular Automata From First Principles 37: Learn the Local Update Rule
Cellular Automata From First Principles 36: Make the Automaton Differentiable
Cellular Automata From First Principles 35: Flow-Lenia and Mass-Conserving Artificial Life
Cellular Automata From First Principles 34: Damage, Robustness and Persistence

Categories

Tags

Ablation Study Absorbing Knowledge ACL-Verbatim Adaptive Agents Adaptive AI Adaptive AI Pipelines Adaptive AI Systems Adaptive Reasoning Adaptive Reasoning Depth Adaptive Runtime Systems Advantage Advantage-Weighted Learning Advantage-Weighted Regression Adversarial Evaluation Adversarial Review Adversarial Validation Agent Agent Architecture Agent Collaboration Agent Debugging Agent Evaluation Agent Loops Agent Memory Agent Orchestration Agent Planning Agent Reliability Agent Routing Agent Search Agent Security Agent State Agent Swarms Agent-Based Training Loops Agentic AI Agentic Systems Agentic Tree Search Agentic Tree Search Agents AGI AI AI Adoption AI Agents AI Amplification AI and Society AI Application Gap AI Architecture AI Art AI as an Amplifier AI Audit Layer AI Backlash AI Capex AI Co-Scientist AI Coding AI Compression AI Debugging AI Detection AI Distillation AI Distrust AI Economics AI Economy AI Engineering AI Evolution AI Future AI Hallucination AI Image Critique AI Infrastructure AI Memory Systems AI Model Evolution AI Observability AI Orchestration Ai Paper Walkthrough AI Pipelines AI Productivity AI Prototyping AI Provenance AI Reasoning AI Reasoning Framework AI Reasoning Systems AI Reliability AI Research Systems AI Safety AI Scalability AI Self-Evaluation AI Self-Improvement AI Singularity AI System Design AI Systems AI Systems Design AI Training AI vs Human AI Writing AI Writing Systems AI-Assisted Health AI-Assisted Research Alignment via Embeddings Animation Answering Machine Effect Anthropic Append-Only Logs Architecture Arena Competition ARM Artificial Intelligence Artificial Life Arxiv Asset Inflation Asset Prices Asset-Holder Enrichment Asset-Price State Associative Memory Assumption Testing Asymmetric Incidence Asynchronous Updates Attention Attractors Attribution Attribution Hallucination Auditable Reasoning Auditable Search Authenticity Crisis Autogptq Autograd Automated Research Agents Autonomous Intelligence Autonomous Research Agents Autonomous Retraining Autonomy Autoround Backpressure Backpropagation Beam Search Belief Cartridges Benchmarking Best-of-N Betti Numbers Big Tech Bitsandbytes Blossom Engine Bond Yields Bond-Market Confidence Brian's Brain Broadcasting Budgeting Buffers Bulkhead Calibration Canada Economy Canada Housing Cancellation Candidate Ranking Capability Learning Capability Planning Capability Security Capability Systems Capability vs Deployment Capacity Constraints Capacity Growth Capital Gains Capital Inflows Capital per Worker Capstone Cargo Cult Cognition Cartridges Case-Based Reasoning Causal Modeling Causality Cave Generation CBR Cellular Automata Chain of Rubrics Chain of Thought Chaos Checkpointing Chronic Illness Circuit Breaker Citation Verification CiteVQA Citizen Balance Sheet Citizen Solvency Citizen Solvency Model Civilizational Systems Claim Verification Claim-Driven Search Classification Claude Code CLIP CMHC Cnn Co-Ai Framework Code Generation Code Search CodeBERT Codex Coding Agents Cognitive Amplification Cognitive Architecture Cognitive Architectures Cognitive Automation Cognitive Garden Cognitive Graph Cognitive Heartbeat Cognitive Patterns Cognitive Planning Cognitive Runtime Cognitive Search Cognitive State Engineering Cognitive Surgery Collective Motion Command Line Common Sense Reasoning Compensation Complexity Computation Computer Vision Concurrency Confidence Tracking Consistency Score Constitutional Reasoning Construction Throughput Content Explosion Content-Addressable Cognition Context Engineering Context Sensitivity Context-Filtered Reasoning Continuous Cellular Automata Contradiction Detector Contrastive Learning Control Plane Controlled Reasoning Controls Conv2d Convolution Conway's Game of Life Coordination Coq Corporate Tax Ireland Corporation Tax Concentration Cosine Similarity Cost of Living CoT CoT Encyclopedia Cot vs Debate Counterfactuals Critic Agent Critical Thinking Critique Cross-Domain Reasoning Transfer Cross-Modal Analysis Crystal Growth CSO Data Cuda Cumulative Improvement Curriculum Learning Cycle Detection Cycles Dashboard Dashboard Growth Dashboard State Dataloader Debt Cycle Debt Legitimacy Debt Rollover Debt Sustainability Debt-Service Burden Debugging Decentralization Decision Frameworks Decision Lineage Decision Making Deep Learning Deep Learning Deployment Deep Learning Limitations Delta Field Delta Memory Dependency vs Independence Deterministic Gating Deterministic Replay Developer Productivity Developer Tools Differentiable Programming Diffusion Digital Biomarkers Digital Crystal Digital Life Digital Organisms Digital Substrate Dimension-Wise Evaluation Dimensional Scoring Distributed AI Systems Distributed-Systems Document Embedding Strategies Document Profiling Document Scoring Dollar System Domain Classification Domestic Productive Capacity DPO Drift Detection DSPy Dual-Pass Scoring Durable Workflows Dynamic Causal Model Dynamic Chunking Dynamic Model Loading Dynamic Reasoning Dynamic Scoring Dynamics EBT Scoring Economic Constraint Economic Measurement Economic Signals Ecosystem Simulation EDGAR Edge AI Editing Electricity Economy Elementary Cellular Automata Embedding Alignment Embedding Comparison Embedding Compatibility Embedding Protocol Design Embedding Subspaces Embedding-Based Reasoning Embedding-Based Training Embedding-Based Tuning Embeddings Emergence Energy-Based Models Engineering Management Enterprise AI Entity Recognition Entrant Exclusion Entropy Episodic Memory Epistemic Architecture Epistemic Engines Epistemic Fields Epistemic Memory Epistemic Quality Epistemic Scaffolding Epistemic State Error Budgets Eurozone Constraint Evaluation Evaluation Frameworks Event Sourcing Event-Sourced Cognition Evidence Evidence Engine Evidence Memory Evidence Quicksand Evidence-Based AI Evidence-Based Reasoning Evidence-Bound Synthesis Evidential Reasoning Evoloops Evolution Evolutionary Search Executable Cognition Executable Cognitive Kernel Executable Search Execution Traces Expected Value of Information Experience Compiler Experiment Experimental Method Experiments Explainable AI Explainable Analysis External Constraint Extractive QA Extractive Transfer Extrinsic Hallucination Failure Taxonomy False Acceptance Rate Falsification Family Formation FastAPI Fault Tolerance Feature Extraction Feature Importance Federal Revenue Federal-Provincial Dynamics Feedback Loops Feedback Loops in AI Fencing Tokens FFmpeg FFT Filmstrip Fin-R1 Finance Financial Repression Fine-Tuning Finite Computation Fiscal Constraint Fiscal Policy Flow-Lenia Flux Forecasting Forest Fire Formal Verification Format Selection Fp16 Fuel Protests Function Calling Functional Intelligence Functions Future Citizen Balance Sheet Future of Work Game of Life GAP Component GDP per Capita General Reasoner Generalization Generative Art Geometric Machine Learning GILD Integration GILD Training Glider GNI vs GDP Goal-Based Learning Goal-Conditioned Evaluation Goal-Conditioned Scoring Goal-Driven AI Goodhart’s Law Gpt Gpu Graceful Degradation Gradients Graph of Thoughts Graph-Based Memory Graph-Based Reasoning Gray Scott GrepSeek Grounded Verification Growth Growth Functions GRPO Gru GSM8K H-Net Chunking Hackathon Hallucination Energy Hallucination Mitigation Hallucination Reduction HaluEval Hash-Verified State Haystack Health Systems Hexagonal Grid Hidden State Hierarchical Cognition Hierarchical JEPA Hierarchical Memory Hierarchical Memory Systems Hierarchical Reasoning High-Trust AI Systems History House-Price-to-Income Household Debt Household Formation Household Fragility Housing Access Housing Completions Housing Crisis Housing Supply Hrm HRM Architecture Hugging Face Human Agency Human Escalation Human Feedback Human in the Loop Human Value Human-AI Collaboration Human-AI Interaction Hybrid AI Systems Hydra Config ICL Scaffolding ICL Training Pipelines Idempotency IFAC Image Generation Image Understanding In-Context Learning Incident Response Inference Speed Inflation Information Information Theory Infrastructure Capacity Inheritance Inspectable AI Inspectable Models Int4 Int8 Intelligent Grep Intelligent Retraining Intent Interest Burden Interest Rate Shock Interest Rates Interest vs Revenue Interest-to-Revenue Interfaces Intergenerational Burden Interpretability Intrinsic Hallucination Ireland Economy Irish Fiscal Policy Irish Housing Iterative Analysis Jitter Json Validation Kernels Knowledge Distillation Knowledge Graph Knowledge Graphs Knowledge Ingestion Knowledge Management Knowledge Measurement Knowledge Scoring Language Models Large Language Models Latent Variables Lean Leanstral Learning-From-Learning Leases Least Privilege Least-Privilege AI LeCun Architecture Legacy Debt Lenia Life Life-Like Cellular Automata Lightweight AI Litellm Llama Factory Llama-Factory Quantization Llm LLM Agents LLM Alignment LLM Arbitration LLM Evaluation LLM Governance LLM Judgement LLM Pipeline LLM Routing LLM Supervision LLM Validation LLMs Local Models Logistic Regression Logits Long-Term AI Memory LoRD Distillation Low-Resource LLMs Machine Learning Macro Economics Macroeconomic Analysis Macroeconomic Modeling Managed Continuity MARS Master–pupil Architecture Material Loss Material State Matplotlib Mazes MCTS Measurement Measurement Crisis Memento Paper Memory Memory Attribution Memory Composition Memory Diffing Memory Drift Memory Governance Memory Graph Memory Health Evaluation Memory Provenance Meta-Agents Meta-Learning Meta-Prompting Meta-Reasoning Metacognition in AI Metacognitive Awareness Metrics Mirror Machine Mixture of Agents Mixture of Experts ML Evaluation Model Alignment Model Architecture Model Comparison Model Compression Model Development Model Distillation Model Head Specialization Model Interpretability Model Monitoring Model Optimization Model Routing Model Selection Model Switching Model Tuning Engines Model Validation Modified Domestic Demand Modular Embeddings Modular Scoring Moment Replay Monetary Policy Monotone Calibration Monte Carlo Tree Search Morphogenesis Morphology Movie Generation MR.Q MRQ MRQ Evaluation MRQ Feedback Loops MRQ Models MRQ Scoring Multi Channel Multi-Agent Multi-Agent Systems Multi-Axis Evaluation Multi-Dimensional Scoring Multi-Model Reasoning Multi-Stage Reasoning Multi-Step Agents Multidimensional Scoring Multihead Attention Multimedia Multimodal AI Multimodal Representation Multinational Concentration Multistrategy Reasoning National Champions NER Retriever Nested Reasoning Loops Neural Cellular Automata Neural Network From Scratch Neural Networks NewsEdits Nexus Nlp Nn.Module NOVELSEEK Num_workers NumPy Object Detection Object Tracking Objective Function Observability Observable Cognition OECD Pillar Two Ollama OOD Detection Open Source AI Open-Ended Evolution OpenCV Opinion Optimization Optimizers Orchestrator Outlier Ownership Access PACS Pairwise Evaluation PaperSearch Parallelism Parameter Search Parameters Parkinsons Path Dependence Pathfinding Patient Support Pattern Detection Pattern Identity Peft Per-Capita GDP Performance Permute Persistence Persistent Cognition Persistent Homology Perturbation Perturbation Testing Pgvector Phenomena Phos PHOS VPM Phōs PiHead Optimization Pin_memory Pipeline Learning Pipeline Optimization Pipeline Tuning Plan Traces Planner Executor Planning PlanTrace Platform Engineering Policy Policy Constraints Policy Learning Policy Networks Policy Optimization Policy Refinement Policy Simulation Policy Synthesis Policy Trade-Offs Policy-Based Evaluation Policy-Bounded AI Pollinator Agent Population Growth Population-Capacity Gap Pose Estimation Postgres PostgreSQL Predator Prey Predictive World Models Preference Learning Preference Modeling Primitive Decomposition Primitive Reasoning Privacy-Preserving Search Procedural Generation Procedural Learning Procedural Reasoning Process Production Production-Ai Productive Transfer Productivity Productivity Gap Productivity Growth Profiling Projection Geometry Prompt Compiler Prompt Engineering Prompt Injection Prompt Optimization Prompt Tuning Proof Assistants Proof Search Provenance Provenance Enforcement Public Capital Public Investment Public-Service Capacity Pupil Models Python Python Ai Pytorch Q Learning Q Value Q-Learning With Embeddings Quality Model Quantization Techniques RAG RAG Verification Ranking Raspberry Pi AI Rate Limiting Reaction Diffusion Real Growth Real Wage Power Reasoning Reasoning Agents Reasoning Failure Analysis Reasoning Geometry Reasoning Models Reasoning Pathway Analysis Reasoning Provenance Reasoning Strategies Reasoning Systems Reasoning Trace Encoder Reasoning Traces Reasoning Verification Reconciliation Recurrent Neural Networks Recurrent Reasoning Blocks Recursive Models Recursive Search Recursive Self-Improvement Reference Gap Reference-Grounded AI Refinancing Risk Reflection Reflection Agents Reflective AI Regeneration Regression Tuner Regressive Transfer Regularized Training Reinforcement Learning Reinforcement-Based Scoring Release-Engineering Relevance Gap Reliability Reliability Engineering Reliable Revenue Rent Burden Reoccupation Repair Repair Loops Replay Replay vs Snapshot Equivalence Replayable Reasoning Reports Representation Learning Reproducibility Research Automation Research Filtering Research Reproducibility Reshape Resource Management Retention Policy Retrieval Retrieval Is Not Proof Revenue Concentration Revenue Quality Reversible Systems Revision Reward Modeling Rhetoric RHLF Risk Risk Management RIVAL Framework Rmsnorm RMSNorm Stability Robustness Rollback Routing Rubric Classification Rubric-Based Evaluation Rule 110 Rule 184 Rule 30 Rule Space Rule-Based Reasoning Runtime Epistemics Runtime Intelligence Runtime Search Sae Safety Sandboxing Savings Resilience Scarcity Scenario Analysis Scheduling Scientific Research SCM Scoped Search Scorable Score Convergence Scoring Pipelines Scoring Stack Search Search as Cognition Search Biasing Search Self-Play Search Topology Selection Self Consistency Self-Improvement Self-Improvement Loop Self-Improving Agents Self-Improving AI Self-Improving AI Systems Self-Improving Systems Self-Learning Self-Referential AI Self-Reflection Self-Reflective Agents Self-Replication Self-Reproduction Self-Supervised Learning Self-Tracking Self-Tuning AI Self-Tuning Loops Self-Tuning Systems Semantic Compression Semantic Drift Semantic Memory Semantic Retrieval Semantic Vector Tuning Sensitivity Sensitivity Analysis Sensitivity Score Shared Canonical Metrics Sharpening SICQL SICQL Integration SICQL Models Signalling Similarity Metrics Simulation SIS SLO Small Model Tuning SmartAnswer Smolagents Snapshot Verification Software Architecture Software-Engineering Sovereign Debt SpaceX Span Extraction Sparse Autoencoders Spatial Intelligence Speculative Execution Sqlite SRE SSP Stable Diffusion State State Capacity State Management State Transition Systems State_dict Statistics Canada Stephanie Stephanie AI Stephanie Framework Stepwise Reasoning Stochastic Generation Stochastic Simulation Stochastic Systems Stock Market Stopping Conditions Strategy Evolution Strategy Memory Strategy Refinement Strict Attributed Accuracy Structural Deficit Structured Outputs Structured Prediction Structured Reasoning Structured Thinking Subconscious AI Systems Summarization Evaluation Superintelligence SVM Evaluation SVM Validation Symbolic AI Symbolic Control Symbolic Learning Symbolic Reasoning Symbolic Representation Symbolic Tuning Symptom Tracking Synthetic Content Synthetic Reasoning System Learning Systemic Risk Systems Analysis Systems Modeling Tax Receipts Tech Culture Technological Change Technology Temporal Consistency Tensor Shapes Terrain Generation Test-Time Compute Testing Text Texture Generation Theorem Proving Theorems Thinking AI Tiny Critic Tiny Recursion Model Tool Calling Tool Loops Tool Use Tools Torch.compile Trace Learning Tracing Trading Traffic Simulation Training Trajectory Learning Transactions Transformers Tree of Thoughts Tree Search Tree-GRPO Trendslop Trust Boundaries Trustworthy AI Trustworthy RAG Turnover Uncertainty Uncertainty-Aware Reasoning Unsupervised Structure US Debt US Integration Valuation Pressure Value Capture Value Function Value Functions Vector Search Vectorization Verbatim Evidence Verifiable AI Verification Verified Attribution Verifier Feedback Video Editing Video Processing View Visual Policy Maps Visual Primitives Visual Proof of Mind Visual Reasoning Visual Thought Maps Visualization VPM VPM-ViT Warranted Search Wearables WebUI Whisper Why Graphs Wikipedia Policy Windfall Tax Revenue Wolfram Classes Workflow Engines Workflow Orchestration Workflow Systems Worldview Modeling Writer Writer Runtime Writing Tools XGBoost YOLO ZeroModel

Social

ernanhughes@gmail.com

© 2026 Programmer.ie: Modern AI programming.