Programmer.ie: Modern AI programming

A site about AI programming

Visual Thought Maps

The Nexus Blossom: How AI Thoughts Turn into Habits

The Nexus Blossom: How AI Thoughts Turn into Habits

AI Engineering, Self-Improving Systems, Cognitive Architectures, Visual Reasoning

November 19, 2025

We turn any text into scorables, grow them into blossoms, and weave them into a living graph. Then we A/B test the graph’s thinking quality.

Recent Posts

The Nexus Blossom: How AI Thoughts Turn into Habits
Search–Solve–Prove: building a place for thoughts to develop
The Space Between Models Has Holes: Mapping the AI Gap
A Complete Visual Reasoning Stack: From Conversations to Epistemic Fields
🔦 Phōs: Visualizing How AI Learns and How to Build It Yourself
Episteme: Distilling Knowledge into AI
🔄 Learning from Learning: Stephanie’s Breakthrough
From Photo Albums to Movies: Teaching AI to See Its Own Progress
Case Based Reasoning: Teaching AI to Learn From itself
SIS: The Visual Dashboard That Makes Stephanie's AI Understandable
ZeroModel: Visual AI you can scrutinize
Everything is a Trace: Stephanie Enters Full Reflective Mode
Layers of thought: smarter reasoning with the Hierarchical Reasoning Model
Stephanie's Secret: The Dawn of Reflective AI
The Shape of Thought: Exploring Embedding Strategies with Ollama, HF, and H-Net
Getting Smarter at Getting Smarter: A Practical Guide to Self-Tuning AI
Epistemic Engines: Building Reflective Minds with Belief Cartridges and In-Context Learning
Self-Improving AI: A System That Learns, Validates, and Retrains Itself
Teaching Tiny Models to Think Big: Distilling Intelligence Across Devices
Agent Architectures: Chapter 2
Compiling Thought: Building a Prompt Compiler for Self-Improving AI
Agent Architectures: Chapter 1
Thoughts of Algorithms
Document Intelligence: Turning Documents into Structured Knowledge
Learning to Learn: A LATS-Based Framework for Self-Aware AI Pipelines

Categories

Tags

Ablation Study Absorbing Knowledge Adaptive Agents Adaptive AI Adaptive AI Pipelines Adaptive AI Systems Adaptive Reasoning Adaptive Reasoning Depth Advantage-Weighted Learning Advantage-Weighted Regression Agent Agent Architecture Agent Collaboration Agent Orchestration Agent Swarms Agent-Based Training Loops Agentic Tree Search Agentic Tree Search AI AI Art AI Co-Scientist AI Compression AI Debugging AI Distillation AI Evolution AI Model Evolution AI Observability Ai Paper Walkthrough AI Provenance AI Scalability AI Self-Evaluation AI Training Alignment via Embeddings Arena Competition ARM Artificial Intelligence Arxiv Attribution Autogptq Automated Research Agents Autonomous Intelligence Autonomous Research Agents Autonomous Retraining Autoround Belief Cartridges Betti Numbers Bitsandbytes Blossom Engine Calibration Cartridges Case-Based Reasoning CBR Chain of Rubrics Co-Ai Framework Cognitive Architecture Cognitive Architectures Cognitive Garden Cognitive Heartbeat Cognitive Planning Cognitive Surgery Command Line Common Sense Reasoning Confidence Tracking Contrastive Learning CoT CoT Encyclopedia Cot vs Debate Cross-Domain Reasoning Transfer Curriculum Learning Cycle Detection Dashboard Debugging Deep Learning Deep Learning Deployment Deep Learning Limitations Delta Field Dimension-Wise Evaluation Dimensional Scoring Distributed AI Systems Document Embedding Strategies Document Profiling Document Scoring Domain Classification DPO DQN DSPy Dual-Pass Scoring Dynamic Chunking Dynamic Model Loading Dynamic Reasoning Dynamic Scoring EBT Scoring EDGAR Edge AI Embedding Alignment Embedding Comparison Embedding Compatibility Embedding Protocol Design Embedding-Based Reasoning Embedding-Based Training Embedding-Based Tuning Energy-Based Models Entity Recognition Epistemic Architecture Epistemic Engines Epistemic Fields Epistemic Memory Epistemic Quality Epistemic Scaffolding Evidential Reasoning Explainable AI FastAPI Feedback Loops Feedback Loops in AI FFmpeg Filmstrip Fin-R1 Finance Fine-Tuning Format Selection Fp16 Functions GAP Component General Reasoner GILD Integration GILD Training Goal-Based Learning Goal-Conditioned Evaluation Goal-Conditioned Scoring Goal-Driven AI Graph of Thoughts GRPO H-Net Chunking Haystack Hierarchical Cognition Hierarchical JEPA Hierarchical Memory Hierarchical Memory Systems Hierarchical Reasoning HRM HRM Architecture Hugging Face Human-AI Interaction Hydra Config ICL Scaffolding ICL Training Pipelines Image Generation In-Context Learning Inference Speed Int4 Int8 Intelligent Retraining Jitter Knowledge Distillation Knowledge Graph Knowledge Graphs Knowledge Ingestion Knowledge Management Knowledge Measurement Knowledge Scoring Large Language Models Latent Variables Learning-From-Learning LeCun Architecture Litellm Llama Factory Llama-Factory Quantization Llm LLM Alignment LLM Arbitration LLM Evaluation LLM Judgement LLM Pipeline LLM Supervision LLM Validation LLMs Logits LoRD Distillation Low-Resource LLMs Machine Learning MARS Master–pupil Architecture Measurement Memento Paper Memory Graph Meta-Learning Meta-Prompting Meta-Reasoning Metacognition in AI Metacognitive Awareness Mirror Machine Model Alignment Model Comparison Model Compression Model Distillation Model Head Specialization Model Monitoring Model Optimization Model Switching Model Tuning Engines Modular Embeddings Modular Scoring Monotone Calibration MR.Q MRQ MRQ Evaluation MRQ Feedback Loops MRQ Models MRQ Scoring Multi-Agent Systems Multi-Dimensional Scoring Multidimensional Scoring Multimedia Multimodal Representation Multistrategy Reasoning NER Retriever Nested Reasoning Loops Neural Networks Nexus Nlp NOVELSEEK Ollama OOD Detection Open Source AI Opinion Orchestrator PACS Pairwise Evaluation PaperSearch Peft Persistent Homology Pgvector Phos PHOS VPM Phōs PiHead Optimization Pipeline Optimization Pipeline Tuning Plan Traces PlanTrace Policy Refinement Policy Synthesis Pollinator Agent Postgres PostgreSQL Predictive World Models Preference Learning Preference Modeling Prompt Compiler Prompt Engineering Prompt Optimization Prompt Tuning Pupil Models Python Ai Pytorch Q-Learning With Embeddings Quantization Techniques Rag RAG Verification Raspberry Pi AI Reasoning Reasoning Failure Analysis Reasoning Pathway Analysis Reasoning Strategies Reasoning Trace Encoder Reasoning Traces Recurrent Reasoning Blocks Reflection Agents Reflective AI Regression Tuner Regularized Training Reinforcement Learning Reinforcement-Based Scoring Reports Representation Learning Research Automation Research Filtering Retention Policy Reward Modeling RHLF RIVAL Framework RMSNorm Stability Routing Rubric Classification Rubric-Based Evaluation Rule-Based Reasoning Sae Scientific Research SCM Scorable Score Convergence Scoring Pipelines Scoring Stack Search Self-Play Self-Improvement Self-Improvement Loop Self-Improving Agents Self-Improving AI Self-Improving AI Systems Self-Learning Self-Referential AI Self-Reflective Agents Self-Supervised Learning Self-Tuning AI Self-Tuning Loops Self-Tuning Systems Semantic Vector Tuning Shared Canonical Metrics Sharpening SICQL SICQL Integration SICQL Models SIS Small Model Tuning SmartAnswer Smolagents Spatial Intelligence Sqlite SSP Stable Diffusion Stephanie Stephanie AI Stephanie Framework Stepwise Reasoning Strategy Evolution Strategy Refinement Structured Prediction Subconscious AI Systems SVM Evaluation SVM Validation Symbolic AI Symbolic Control Symbolic Learning Symbolic Reasoning Symbolic Tuning Technology Text Theorems Thinking AI Tiny Recursion Model Tools Trading Tree-GRPO Uncertainty Uncertainty-Aware Reasoning Verification Video Editing Video Processing Visual Policy Maps Visual Proof of Mind Visual Thought Maps Visualization VPM VPM-ViT WebUI Whisper Worldview Modeling Xgboost ZeroModel

Social

ernanhughes@gmail.com

© 2025 Programmer.ie: Modern AI programming.