The full programmer.ie article history. Learning paths and AI prompts are curated separately; this archive keeps the broader research, experiments and technical writing easy to scan.
Build a Production AI Agent From First Principles: The Complete Reference Architecture We have spent this series adding mechanisms only when a specific failure demanded them. We started with a model call. Then we added …
Advanced Agents From First PrinciplesTreat agent behavior like a production interface: define behavioral contracts, test compatibility across models, prompts, tools, memory, routers and verifiers, then promote changes through explicit release gates.
Advanced Agents From First PrinciplesLearn how to detect silent behavioral regressions in agent systems caused by model, prompt, router, verifier, retrieval, policy and data-distribution drift, then roll back safely using evidence rather than intuition.
Advanced Agents From First PrinciplesLearn how to contain failing model, browser, retrieval, verifier, database and API dependencies with circuit breakers, bulkheads, bounded retries and graceful degradation.
Advanced Agents From First PrinciplesLearn how to schedule many concurrent AI agent runs across shared models, GPUs, browsers, tools and external APIs using admission control, quotas, fairness, priorities, reservations and backpressure.
Advanced Agents From First PrinciplesCan Your Agent Coordinate Across Machines Without Duplicating Work? A single-process agent can already be complicated. It can plan. It can search. It can launch speculative branches. It can cancel losing work. It can …
Advanced Agents From First PrinciplesAdvanced Agents From First Principles 19: Can Your Agent Explore in Parallel Without Creating Chaos? Use Speculative Execution and Early Cancellation A production agent often has more than one useful thing it could do …
Advanced Agents From First PrinciplesLearn how to choose the next observation, diagnostic, retrieval, experiment, tool call, or verifier check by estimating how much it could change the agent's decision relative to its cost.
Advanced Agents From First PrinciplesStop treating agent confidence as one scalar. Decompose uncertainty into interpretation, evidence, routing, state, candidate, and verification uncertainty so the runtime can buy the right next action.
Advanced Agents From First PrinciplesLearn how to allocate model calls, search nodes, tool executions, verifier work, latency and money dynamically instead of relying on fixed agent budgets.
Advanced Agents From First PrinciplesLearn how to optimize routing, search depth, escalation, model selection and stopping policies from verified trajectories while keeping the control layer small, interpretable and reversible.
Advanced Agents From First PrinciplesLearn how to turn verified agent trajectories into safer routing, search and budget policies without reinforcing the system's own mistakes.
Advanced Agents From First PrinciplesLearn how to debug advanced agent systems with decision lineage, trajectory traces, routing and pruning reasons, cost attribution, verifier evidence, replay, and failure localization.
Advanced Agents From First PrinciplesLearn how to benchmark MCTS, Tree of Thoughts, self-consistency, debate, routing and adaptive agent systems without confusing extra compute with better architecture.
Advanced Agents From First PrinciplesA practical framework for choosing between self-consistency, Tree of Thoughts, beam search, MCTS, evolutionary search, specialist routing, debate, planner-executor-critic systems, adaptive agents and mixtures of agents.
Advanced Agents From First PrinciplesThe final lesson in Advanced Agents From First Principles: start with the smallest production agent that preserves authority, authoritative state, verification and traceability, then add complexity only when measured failures justify it.
Advanced Agents From First PrinciplesA production-agent architecture that separates control-plane policy from execution-plane reasoning: intent, competence, authority, placement, budgets, reliability, releases, security and escalation remain enforceable …
Advanced Agents From First PrinciplesA practical architecture for multi-agent coordination: explicit ownership, delegation, contracts, commitment transfer, shared intent, evidence provenance, conflict handling, deadlock prevention, and independent …
Advanced Agents From First PrinciplesA practical security architecture for production agents: separate data from authority, classify trust, scope credentials and capabilities, preserve provenance, isolate generated code, resist prompt injection, and keep …
Advanced Agents From First PrinciplesA practical architecture for agent workflows that span systems without a global transaction: classify side effects, prepare carefully, commit with identity, verify externally, compensate when possible, reconcile …
Advanced Agents From First PrinciplesA practical architecture for long-running agents: keep workflow state durable while treating models and workers as disposable, with explicit waits, retries, timers, human approvals, checkpoints, commitments, cancellation …
Advanced Agents From First PrinciplesA practical architecture for separating goals, plans, commitments, tasks and actions in long-running agents so replanning, cancellation, handoff and external obligations remain correct.
Advanced Agents From First PrinciplesA production architecture for intent versioning, supersession and cancellation in long-running agents: stop obsolete work, preserve committed effects, reconcile partial actions, and prevent stale goals from retaining …
Advanced Agents From First PrinciplesA practical architecture for keeping long-running agents from acting on stale assumptions: classify state by freshness, track version vectors, detect conflicts, revalidate before consequential actions, and force …
Advanced Agents From First PrinciplesA practical architecture for portable agent execution state: checkpoint long-running runs, transfer ownership safely across workers and providers, preserve evidence and authority, and reject migrations that cannot be …
Advanced Agents From First PrinciplesA practical placement architecture for advanced agents: route work across local and frontier models, providers, regions, GPUs, browser pools and specialist runtimes using demonstrated competence, verifier availability, …
Advanced Agents From First PrinciplesA practical capability-dependency architecture for advanced agents: identify shared primitives that unlock many capabilities, quantify leverage, expose correlated-failure hotspots, and invest in platform components …
Advanced Agents From First PrinciplesA practical framework for deciding which agent capabilities are worth acquiring: rank missing capabilities by user value, verifier availability, reliability risk, acquisition cost, maintenance burden, and the quality of …
Advanced Agents From First PrinciplesA practical architecture for sandboxed capability acquisition: let agents explore tasks outside their validated competence envelope, accumulate externally verified evidence, and propose capability expansion without ever …
Advanced Agents From First PrinciplesA practical framework for competence envelopes in production agents: distinguish uncertainty from lack of validated competence, detect out-of-distribution tasks, contract authority when evidence is weak, and expand …
Advanced Agents From First PrinciplesA practical architecture for agent authority boundaries: decide what an agent may do autonomously, when it must escalate, what evidence a human reviewer needs, and how to avoid turning human approval into …
Advanced Agents From First PrinciplesA practical framework for deciding where to spend the next engineering hour in an advanced-agent system: rank remediation by expected reduction in verified reliability loss, severity, recurrence, blast radius, confidence …
Advanced Agents From First PrinciplesA practical reliability framework for advanced agents: define verified-success SLOs, false-success ceilings, UNKNOWN budgets, latency and cost targets, then use error-budget burn to decide when to ship capability and …
Advanced Agents From First PrinciplesA practical incident-forensics workflow for advanced agents: reconstruct the run, find the earliest divergence, distinguish root cause from downstream symptoms, measure blast radius, and prove that a remediation would …
Advanced Agents From First PrinciplesA production agent fails on Tuesday. You inspect it on Wednesday and cannot reproduce the failure. Three weeks later someone asks a harder question: What exactly did this agent see, which release was running, which tools …
Advanced Agents From First PrinciplesBuild adaptive agent runtimes that start cheap, measure uncertainty and failure, and escalate selectively into deeper reasoning, more samples, search, stronger models or specialist review only when the evidence justifies …
Advanced Agents From First PrinciplesYou have a working agent. Then you add retrieval. Then memory. Then Best-of-N. Then critique and revision. Then Tree of Thoughts. Then MCTS. Then specialist models. Then adversarial review. Then a planner, executor, …
Advanced Agents From First PrinciplesLearn how to turn verified agent trajectories into safer future policies without confusing memory with learning or poisoning the system with bad experience.
Advanced Agents From First PrinciplesDoes One Agent Plan, Execute and Judge Its Own Work? Build a Planner-Executor-Critic Architecture A single model can often do all of these things: understand a task, decide what to do, execute a tool call, inspect the …
Advanced Agents From First PrinciplesA common agent architecture starts simply: request ↓ model ↓ action That simplicity is valuable. It should be your default. But eventually you may notice something strange. The same model is being asked to do everything: …
Advanced Agents From First PrinciplesA common failure in search-based agents is easy to miss. The agent generates several plausible branches. It scores them. One branch looks weak. So the runtime prunes it. Later, you discover that the discarded branch was …
Advanced Agents From First PrinciplesA reasoning agent can fail even when every individual step looks plausible. The problem is often not that the model cannot produce a good line of reasoning. The problem is that it commits too early. It chooses one …
Advanced Agents From First PrinciplesA reasoning agent gives you one answer. You run it again. It gives you another. You change nothing important: same task, same tools, same model family, same broad context. Yet the result changes. That is not necessarily …
Advanced Agents From First PrinciplesMost developers first encounter chain of thought as a prompting trick: Think step by step. That framing is too shallow for agent engineering. For an advanced agent, the useful idea is not that the model should produce a …
Advanced Agents From First PrinciplesAdvanced Agents From First Principles 00: When Should You Use an Advanced Agent Architecture? You built an agent. It can: call tools, maintain state, plan, revise its own work, search over alternatives, remember useful …
Advanced Agents From First PrinciplesAn AI agent says: Done. The task is complete. That sentence is almost worthless. The agent may have: edited the wrong file, changed the right file incorrectly, skipped part of the request, broken another subsystem, …
Agents From First PrinciplesAn AI agent often fails for a surprisingly ordinary reason: it commits too early. It finds one plausible next action, follows it, and then spends the rest of the run trying to make that first choice work. That can look …
Agents From First PrinciplesAI Agent Forgets Previous Work? Add Working, Semantic and Episodic Memory An agent can use the right model, call the right tools, execute the right plan, and still behave as if nothing that happened five minutes ago …
Agents From First PrinciplesAn agent can have a perfectly capable model and still behave badly because its tools are badly designed. This is one of the most common agent failures in production: user goal ↓ agent ↓ wrong tool ↓ wrong action The …
Agents From First PrinciplesAn AI agent that keeps calling the same tool, revisiting the same page, rewriting the same file, or repeatedly saying “I’ll try again” is not displaying persistence. It is displaying a control-flow bug. This is one of …
Agents From First PrinciplesA surprising number of agent failures are not really model failures. The model may be perfectly capable of writing each individual step. The failure happens because the system tries to decide what to do and do it at the …
Agents From First PrinciplesAn AI agent can fail in a particularly frustrating way: it produces an answer that is almost right, you ask it to improve the answer, and it produces another answer with the same underlying defect. Sometimes the wording …
Agents From First PrinciplesOne of the first things you notice when you build anything around a large language model is that the same prompt does not always produce the same quality of answer. Sometimes the first response is excellent. Sometimes it …
Agents From First PrinciplesIf your agent sometimes invents a tool name, omits a required argument, returns malformed JSON, or produces an action that looks plausible but cannot actually be executed, the problem is usually not “the agent is …
Agents From First PrinciplesWhat Is an Agent, Really? This is the first post in Agents From First Principles. It follows two earlier series. In PyTorch: Zero to Hero, we worked upward from tensors, autograd and neural-network building blocks until …
Agents From First PrinciplesWhich Model Should You Use? MR.Q, EBT, SICQL, HRM, Tiny and PACS Compared This is the final post in Models From First Principles. The earlier posts asked a sequence of architectural questions: how do we score a …
Models From First PrinciplesPACS — Building an Optimizer From Gradient Statistics So far in Models From First Principles, every post has asked some version of the same question: What should the model compute? MR.Q gave us a scalar quality estimate. …
Models From First PrinciplesInside Tiny: Residual Blocks, Attention and Sparse Autoencoders In the previous post, we built a compact recursive model around one idea: context + candidate + latent state ↓ projection ↓ reusable core ↓ proposed update …
Models From First PrinciplesTiny — Recursive Reasoning With a Small Neural Network The previous post introduced a much more ambitious architecture. Instead of taking one representation and predicting from it once, the Hierarchical Reasoning Model …
Models From First PrinciplesHRM — Hierarchical Reasoning With Fast and Slow Recurrent State The previous models in this series were mostly one-pass models. MR.Q took two embeddings and produced one score. EBT kept the same basic structure but added …
Models From First PrinciplesSICQL — Building a Model From Q, V and Policy Networks In the previous post we took the MR.Q idea and expanded it into something richer. Instead of asking one question of a shared representation, EBT asked several: How …
Models From First PrinciplesEBT — From One Score to Q, V, Policy and Advantage In the previous post we built MR.Q: a small model that takes a context embedding and a response embedding, combines them, and predicts one scalar. That architecture is …
Models From First PrinciplesMR.Q — Building a Neural Quality Model From Two Embeddings In the previous post, we established the core idea behind this series: A complicated model becomes understandable when you recursively decompose it into smaller …
Models From First PrinciplesThe Model Inside the Model This is the first post in Models From First Principles. The previous PyTorch: Zero to Hero series worked from the bottom up. We started with tensors. Then gradients. Then nn.Module. Then data …
Models From First PrinciplesBuild a Small GPT-Style Language Model From Scratch in PyTorch This is the final post in the PyTorch: Zero to Hero series. We have spent the previous posts learning the machinery underneath PyTorch: tensors and shapes; …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 09 At this point in the series, the model runs. That does not mean it runs well. A training loop can be correct and still waste most of the machine. A model can fit in memory and still spend …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 08 Your model runs. The loss is finite. Nothing crashes. And it still does not learn. This is one of the most frustrating states in machine learning because there is no stack trace telling …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 07 Attention code is where tensor-shape mistakes stop being annoying and start becoming architectural. A CNN usually makes its dimensional assumptions fairly obvious. Attention does not. A …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 06 CNN code is usually easy to write. CNN shape bugs are usually easy to create. A typical failure looks like this: RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 05 A fast model with a slow input pipeline is still a slow training system. One of the most common PyTorch performance failures looks like this: GPU utilization: 20% → 95% → 10% → 90% → 15% …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 04 In the previous post we built a neural network using raw tensors and autograd. Now we are going to add the abstraction PyTorch expects almost every real model to use: class …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 03 Most PyTorch tutorials begin with something like this: import torch.nn as nn model = nn.Sequential( nn.Linear(2, 16), nn.ReLU(), nn.Linear(16, 2), ) That is useful code. It is also hiding …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 02 In the previous post we treated tensor shapes as a debugging problem rather than a mathematical vocabulary exercise. We are going to do the same thing with autograd. If you use PyTorch for …
PyTorch: Zero to HeroPyTorch: Zero to Hero — Step 01 Most PyTorch bugs are not really “AI bugs”. They are shape bugs. You expected: [batch, features] but actually had: [batch, sequence, features] You expected two tensors to line …
PyTorch: Zero to HeroPyTorch: Zero to Hero This is Step 0 of a practical PyTorch series that starts with tensors and ends with building a small language model from scratch. The goal is not to learn a collection of PyTorch commands. The goal …
PyTorch: Zero to HeroZeroModel is an attempt to compile useful parts of intelligence into identified, portable, inspectable decision artifacts — and to preserve enough evidence around those artifacts that we can reproduce, challenge and …
A multi-agent system can look sophisticated while every agent quietly repeats the same mistake. That is one of the most dangerous failure modes in advanced agent architectures. You ask one model to solve the problem. …
Advanced Agents From First PrinciplesEmbeddings are everywhere in modern AI. They power semantic search, retrieval-augmented generation, recommendations, clustering, duplicate detection, code search, memory systems, and many of the mechanisms through which …
For decades, the technological singularity has been presented as a future event. At some point, an artificial intelligence would become as intelligent as a human being, improve itself, become superintelligent and …
What happens when a system stops asking an AI for the same directions repeatedly, and starts placing signs where decisions need to be made? ZeroModel in One Image Most AI systems repeatedly invoke a policy: observe the …
We Trained a Model on Editorial Choices to See Whether It Learned What Happened Next Most preference-learning systems use a choice to change the future. A model produces two responses. A human selects one. The chosen …
Evidence that the alternative a writer rejects can help predict the future stability of what they retain.
An AI-assisted model of how GDP optics, housing pressure, debt rollover, and fiscal constraint can hide citizen insolvency. 1. A Country Is Its Citizens A country is not its GDP, its bond market, its housing index, or …
Most AI systems answer and move on. The next step is different: preserve the reasoning state, replay it, measure whether it improves, and keep only what survives verification. Summary Most AI workflows still treat …
What this post argues The U.S. does not merely like a high stock market. It increasingly needs one. The stock market has become an amplifier inside the largest federal revenue pipe: individual income tax. When asset …
Capability is real. Application is the bet The AI economy is no longer theoretical. AI is now showing up in financial statements, capex plans, and reported investment gains. The largest technology companies in the world …
TL;DR Modern AI systems often retrieve nearby text and generate confident answers, but that is not the same as proof. A citation can be real, the answer can be correct, and the evidence can still fail to support the …
From visual primitives to context-filtered reasoning, grounded verification, and AI movie repair TL;DR This post argues that AI reasoning should not operate over everything it can see, read, or detect. It should operate …
A systems-level analysis of AI, structural economic constraint, managed continuity, and the decentralization of human capability in an era of slowing growth.
AI systems today have no idea why their own memory changes, that’s the problem we are trying to solve in this post. Summary Most AI memory systems start from a practical place: retrieval. Retrieval is useful, scalable, …
TL;DR Codex Manager uses AI to generate code as an artifact, then tests that artifact, diagnoses what happened, and repairs the prompt state that produced it. The code is not the thing being optimized directly. The …
A Cognitive Graph is an enhanced chat log one that doesn’t just record what was said, but structurally preserves how thoughts, decisions, alternatives, and artifacts evolve over time, making the whole history replayable …
AI turns language into an interface for implementation. 1. The Builder’s World There is a version of AI people talk about. And then there is the version you discover when you actually use it consistently. They are not …
We’re not teaching machines to think. We’re teaching ourselves to build thinking systems. 🎨 From AI Assistants to Controlled Cognitive Amplification Most people use AI to write faster. But the real opportunity isn’t …
Why you already know what you’re about to read isn’t real and what to do about it. Imagine a small red badge on every article, every design, every conversation: AI-Generated Content. Before you read a single word, you …
🧩 1. TLDR AI doesn’t just hallucinate. Sometimes it gives answers that are fluent, safe… and completely useless. Most discussions about AI failure focus on hallucination: making things up getting facts wrong …
A practical, AI-assisted system for living with Parkinson's. Track patterns, stabilize routines, and adapt intelligently one day at a time. Not a cure. A fighting chance.
Abstract Recent analysis of U.S. fiscal dynamics suggests a structural constraint emerging around the end of this decade, driven by rising interest burdens relative to government revenue. This paper explores the …
Using AI to Decode Symbols Without Assuming Meaning Executive Summary: From Symbol to System We set out to understand a single image. We ended up building a system that can understand structure itself. We started with a …
Executive Summary Canada’s fiscal position looks stable on paper. Headline interest costs consume only ~10.6% of federal revenue. But this ratio masks a structural reality: the engine that drove revenue growth has …
Executive Summary This post applies a simple, testable framework to Ireland’s fiscal system: Fiscal constraint emerges when the cost of debt rises relative to the revenue supporting it. In large, stable systems …
How We Used AI to Analyze When U.S. Debt Becomes a Constraint Executive Summary We demonstrate a human + AI research process. AI was used to: refine the question identify the correct metric expose assumptions and test …
Summary Dynamic AI systems face a hidden failure mode: they can learn from their own mistakes. If every output is allowed into memory, stochastic errors do not stay local they accumulate. In earlier posts, I argued that …
🧭 Summary Most modern AI systems treat intelligence as something stored inside a model. A neural network is trained on massive datasets, its weights are adjusted, and those weights become the system’s knowledge. When the …
Read enough AI prose and a rhythm starts to appear. Not fear. Not relief. Not strategy.Once you see it, you cannot unsee it. 🧠 Abstract Large language models frequently produce rhetorical constructions such as “not fear, …
Building a Self-Improving AI: Cooperative ERL and Embed-RL in a Trace-Native Architecture 1. The Problem Most self-improving AI systems fail for one of three reasons: First, scalar reward collapse. Traditional …
🚀 Summary This post presents the current research draft and implementation of a geometric framework for bounding stochastic language models through deterministic policy enforcement. The central contribution is a scalar …
⏰ TLDR This work shows that the hardest part of using AI in high-trust environments is not the model, but the policy. Once editorial policy is made explicit and executable, AI systems become interchangeable the real …
😶🌫️ Summary This post is a quick review of the journey so far. We’re one third of the way through the Self-Learning Systems (100-part) series, and this checkpoint pulls together the first 33 posts and the research …
🥹 0. TL;DR Large language models write fluent explanations even when they’re wrong. Verifying their reasoning usually requires another LLM slow, expensive, and circular. We needed something different: A miniature …
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.
🌌 Summary What if you could see an AI think not just the final answer, but the whole stream of reasoning: every search, every dead end, every moment of insight? We’re building exactly that: a visible, measurable thought …
A step-by-step guide to visualizing AI reasoning from raw metrics to epistemic fields.
From conversations to epistemic fields: the complete stack that makes AI reasoning visible, editable, and scalable.
A step-by-step guide to visualizing AI reasoning from raw metrics to epistemic fields.
Turn conversations into a measurable knowledge signal. Attribute, quantify lift, and build AI that learns from learning.
📖 Summary AI has always been about absorption: first data, then feedback. But even at its best, it hit a ceiling. What if, instead of absorbing inputs, it absorbed the act of learning itself? In our last post, we reached …
🥱 TLDR This post details the implementation of: PACS: Implicit Actor–Critic Coupling via a Supervised Learning Framework for RLVR NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings within our …
✨ Summary Imagine an AI that gets smarter every time it works not by retraining on massive datasets, but by learning from its own reasoning and reflection, just like humans. Most AI systems are frozen in time. Trained …
🔍 The Invisible AI Problem How do you debug a system that generates thousands of database entries, hundreds of prompts, and dozens of knowledge artifacts for a single query? SIS is our answer a visual dashboard that …
“The medium is the message.” Marshall McLuhan We took him literally. What if you could literally watch an AI think not through confusing graphs or logs, but by seeing its reasoning process, frame by frame? Right now, AI …
🔧 Summary In our last post, Layers of Thought: Smarter Reasoning with the Hierarchical Reasoning Model, we introduced a new epistemic lens a way to evaluate not just final answers, but the entire sequence of reasoning …
🤝 Introduction Forget everything you thought you knew about AI reasoning. What you’re about to discover isn’t just another scoring algorithm it’s Stephanie’s first true capacity for thought. …
🌅 Introduction: The Dawn of Self-Reflective AI What if your AI could not only answer questions but also question itself about those answers? Not with programmed doubt, but with genuine self-awareness recognizing when …
🔍 Summary Stephanie, a self-improving system, is built on a powerful belief: If an AI can evaluate its own understanding, it can reshape itself. This principle fuels every part of her design from embedding to scoring to …
🔥 Summary: The Self-Tuning Imperative “We’re drowning in models but starved for wisdom.” Traditional AI stacks: Require constant manual tuning Suffer from version lock-in Can’t explain their …
🔍 Summary: Building the Engine of Understanding This is not a finished story. It’s the beginning of one and likely the most ambitious post we’ve written yet. We’re venturing into new ground: designing epistemic …
🤖 The Static AI Trap Today’s AI systems are frozen in time: trained once, deployed forever. Yet the real world never stops evolving. Goals shift overnight. New research upends old truths. Context transforms without …
🧪 Summary As AI developers, we often face the tradeoff between intelligence and accessibility. Powerful language models like Qwen3 run beautifully on servers but what about on the edge? On devices like Raspberry Pi or …
This is a summary of the second chapter of a book I wrote: Agent Architectures: Advanced Strategies for Intelligent LLM Systems 🤖 Chapter 2 : How to Think With AI Agents Agents aren’t just tools they’re thinking …
How to design a pipeline that turns vague goals into smart prompts 🧪 Summary Why spend hours engineering prompts when AI can optimize its own instructions. This blog post introduces a novel approach toward creating a …
This is a summary of the first chapter of a book I wrote: Agent Architectures: Advanced Strategies for Intelligent LLM Systems 🚀 Introduction to LLM Agents 🤖 What is an LLM Agent? An LLM agent is an intelligent software …
How a self-evolving AI learns to reflect, score, and rewrite its own reasoning 🧪 Summary What if an AI could think not just solve problems, but reevaluate its beliefs in the face of new information? In this post, we …
📖 Summary Imagine drowning in a sea of research papers, each holding a fragment of the knowledge you need for your next breakthrough. How does an AI system, striving for self-improvement, navigate this information …
📖 Summary In this post, we introduce the LATSAgent, an implementation of LATS: Language Agent Tree Search Unifies Reasoning.. within the stephanie framework. Unlike prior agents that followed a single reasoning chain, …
📖 Summary This post introduces a multidimensional reward modeling pipeline built on top of the stephanieanie framework. It covers: ✅ Structured Evaluation Setup How to define custom evaluation dimensions using YAML or …
🧪 Summary “What if AI systems could learn how to improve themselves not just at the level of weights or prompts, but at the level of strategy itself? In this post, we show how to build such a system, powered by …
Summary Chain-of-thought is powerful, but which chain? Short explanations work for easy tasks, long reflections help on hard ones, and code sometimes beats them both. What if your model could adaptively pick the best …
Replicating NOVELSEEKs autonomous research pipeline using modular agents, persistent memory, and evolutionary hypothesis mapping.
🔧 Summary Modern AI systems require more than just raw processing power they need contextual awareness, strategic foresight, and adaptive learning capabilities. In this post, we walk through how we implemented a …
An open-source walkthrough of the General Reasoner agent implemented with local models, rubric-based judging, and multistrategy reasoning pipelines using the stephanie framework.
Most AI systems generate answers. Ours examines how they think. This isn’t just prompt engineering this is structured reasoning at scale. 🔧 Summary Large Language Models are transforming every field, yet their internal …
In this post, I build a self-improving agent that sharpens its own reasoning using MR.Q and structured prompting templates.
This is the first post in a 100-part series, where we take breakthrough AI papers and turn them into working code building the next generation of AI, one idea at a time. 🧾 Summary In this post, I’ll walk through how I …
How I built Clipper a simple, scriptable, open-source tool for generating images with AI prompts using webui_forge.
Cross-Modal Cognitive Mapping A Technical Overview of System Design and Implementation Author: Ernan Hughes Published: April 2025 Abstract Cross-Modal Cognitive Mapping is a new framework designed to extend traditional …
Summary Large Language Models (LLMs) like DeepSeek-R1 show remarkable reasoning abilities, but how these abilities are internally represented has remained a mystery. This paper explores the mechanistic interpretability …
🕒 TL;DR We explore MARS, a multi-agent prompt optimizer using Socratic dialogue. We implement it using DSPy + Fin-R1 + EDGAR giving us an end-to-end financial reasoning pipeline. We deploy the whole thing to Hugging Face …
Introduction Fin-R1 is a new model specifically fine-tuned for financial reasoning, with performance that beats much larger models like DeepSeek-R1. This post will use this model and compare it with phi3 across various …
Introduction Model-free reinforcement learning learns a policy directly from experience, but it can struggle to discover useful representations from sparse or noisy rewards. Model-based reinforcement learning receives a …
Summary Machine learning operates on data. Essentially, it processes data to extract meaningful information, which can then be used to make intelligent decisions. This is the foundation of Artificial Intelligence. The …
Summary Artificial Intelligence (AI) has revolutionized the way we generate and consume text. From chatbots crafting customer responses to AI-authored articles, artificial intelligence is reshaping how we create and …
Summary Could the greatest playwright of all time have secretly shaped one of the most influential religious texts in history? Some believe William Shakespeare left his mark on the King James Bible hidden in plain sight. …
Summary Vector databases are essential for modern AI applications like semantic search, recommendation systems, and natural language processing. They allow us to store and query high-dimensional vectors efficiently. With …
Summary The evolution of technology is driven by protocols structured ways for systems to communicate and interact. The internet, APIs, and even modern databases rely on protocols to function efficiently. Similarly, as …
Summary In AI and data science, knowledge graphs are powerful tools for modeling complex relationships between entities. They enable intelligent querying, recommendation systems, and semantic search. Neo4j, an …
Summary Function calling allows Large Language Models (LLMs) to interact with APIs, databases, and other tools, making them more than just text generators. Integrating LLMs with functions enables you to harness their …
Summary What if AI isn’t just a tool but the foundation of how you work, create, and think? Today there are two distinct ways to approach AI: +AI and AI+. +AI means integrating AI into an existing workflow, business, or …
Summary In this post, I will demonstrate how to set up and use haystack with Ollama. haystack is a framework that helps when building applications powered by LLMs. It offers extensive LLM-related functionality. It is …
Summary In this post I will cover LiteLLM. I used it for my implementation of Textgrad also it was using in blog posts I did about Agents. Working with multiple LLM providers is painful. Every provider has its own API, …
🧩 Summary This post aims to be a comprehensive tutorial on Textgrad. Textgrad enables the optimization of LLM’s using their text responses. This will be part of SmartAnswer the ultimate LLM query tool which I will …
Summary In this blog post I want to fully explore logits and how they can be used to enhance AI applications I want to understand the ideas from this paper: “Is That Your Final Answer? Test-Time Scaling Improves …
Summary This is another component in SmartAnswer and enhanced LLM interface. In this blog post, we introduce a wrapper class, FaissDB, which integrates FAISS with SQLite or any database to manage document embeddings and …
Summary This is part on in a series of blog post working towards SmartAnswer a comprehensive improvement to how Large Language Models LLMs answer questions. This tool will be the source of data for SmartAnswer and allow …
Summary SQLite is one of the most widely used database engines in the world, powering everything from mobile applications (Android, iOS) to browsers (Google Chrome, Mozilla Firefox), IoT devices, and even gaming …
Summary This post is an explanation of this paper:RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment. Generative foundation models, such as Large Language Models (LLMs) and diffusion models, have …
Summary Searching through massive datasets efficiently is a challenge, whether in image retrieval, recommendation systems, or semantic search. Faiss (Facebook AI Similarity Search) is a powerful open-source library …
Summary Imagine you have a dataset of customer profiles. How can you group similar customers together to tailor marketing campaigns? This is where K-Means clustering comes into play. K-Means is a popular unsupervised …
Summary Imagine a world where you simply think of a task, and invisible devices seamlessly execute it. In fact most of what used to be your daily tasks you won’t even think about they will be automatically …
Summary Forecasting future events is a critical task in fields like finance, politics, and technology. However, improving the forecasting abilities of large language models (LLMs) often requires extensive human …
Summary Large Language Models (LLMs) are powerful, but their size can lead to slow inference speeds and high memory consumption, hindering real-world deployment. Quantization, a technique that reduces the precision of …
Summary Large Language Models (LLMs) offer immense potential, but realizing that potential often requires fine-tuning them on task-specific data. This guide provides a comprehensive overview of LLM fine-tuning, focusing …
Summary Visual Studio Code is the most popular editor for development. Jupyter Notebooks is the most widely used way to share, demonstrate and develop code in modern AI development. Debugging code is not just used when …
Summary This post details building a robust web data pipeline using SmolAgents. We’ll create tools to retrieve content from various web endpoints, convert it to a consistent format (Markdown), store it efficiently, …
Summary In this post, we’ll build a Retrieval Augmented Generation (RAG) tool to process the PDF files downloaded from arXiv in the previous post DeepResearch Part 1. This RAG tool will be capable of loading, …
Summary This post kicks off a series of three where we’ll build, extend, and use the open-source DeepResearch application inspired by the Hugging Face blog post. In this first part, we’ll focus on creating an …
Introduction FFmpeg is an incredibly versatile command-line tool for manipulating audio and video files. This post provides a practical collection of useful FFmpeg commands for common tasks. FFmpeg Command Structure The …
Summary This post provides a practical guide to building common neural network architectures using PyTorch. We’ll explore feedforward networks, convolutional neural networks (CNNs), recurrent neural networks …
Summary This post provides a comprehensive guide to prompt engineering, the art of crafting effective inputs for Large Language Models (LLMs). Mastering prompt engineering is crucial for maximizing the potential of LLMs …
Summary In this blog I aim to try building using open source tools where possible. The benefits are price, control, knowledge and eventually quality. In the shorter term though the quality will trail the paid versions. …
Summary This post demonstrates how to automatically transform a scientific paper (or any text/audio content) into a YouTube video using AI. We’ll leverage several powerful tools, including large language models …
Summary In this post I explore Robert Bridson’s paper: Fast Poisson Disk Sampling in Arbitrary Dimensions and provide an example python implementation. Additionally, I introduce an alternative method using Cellular …
Introduction Activation functions are a component of neural networks they introduce non-linearity into the model, enabling it to learn complex patterns. Without activation functions, a neural network would essentially …
Summary In this post I will implement a Support Vector Machine (SVM) in python. Then describe what it does how it does it and some applications of the instrument. What Are Support Vector Machines (SVM)? Support Vector …
Summary This post is about color wars: a grid containing dynamic automata at war until one dominates. Implementation The implementation consists of two core components: the Grid and the CellularAutomaton. 1️⃣ …
44. What does it mean to Fit a Model? Answer Fitting a model refers to the process of adjusting the model’s internal parameters to best match the given training data. It’s like tailoring a suit – you adjust …
Summary The Nagel-Schreckenberg (NaSch) model is a traffic flow model which uses used cellular automata to simulate and predict traffic on roads. Design of the Nagel-Schreckenberg Model Discrete Space and Time: The road …
Summary I started with this paper A developmentally descriptive method forquantifying shape in gastropod shells and bridged the results to a cellular automata approach. An example of the shell we are modelling: Steps 1️⃣ …
Summary This page is the first in a series of posts about Cellular Automata. I believe that we could get the first evidence of AI through cellular automata. A recent paper Intelligence at the Edge of Chaos found that …
Summary Retrieval-Augmented Generation (RAG) is a powerful technique that enhances large language models (LLMs) by allowing them to use external knowledge sources. An Artificial Intelligence (AI) system consists of …
Summary Retrieval-Augmented Generation (RAG) has become the dominant approach for integrating external knowledge into LLMs, helping models access information beyond their training data. However, RAG comes with …
LLM Agents Agents are used enhance and extend the functionality of LLM’s. In this tutorial, we’ll explore what LLM agents are, how they work, and how to implement them in Python. What Are LLM Agents? An agent is an …
Some FREE AI courses on Agents I recommend doing Agents were important in Machine Learning development last year. These are some courses I have done and recommend they are all free. A good reason to do courses and look …
Using Ollama Introduction Ollama is the best platform for running, managing, and interacting with Large Language Models (LLM) models locally. For Python programmers, Ollama offers seamless integration and robust features …
Hugo: A Static Site Generator In this post I give an introduction to what I think is the best static site generator: Hugo. What is Hugo? Hugo is an open-source static site generator written in Go. It takes structured …
1️⃣ Introduction In the era of AI-powered search, retrieval-augmented generation (RAG), and recommendation systems, efficient vector search is a necessity. While many vector databases exist, most require heavy …
An android implementation of [CDB] (https://cr.yp.to/cdb.html) database. With some simple testing I am seeing a five to ten times increase in speed over Sqlite
A derivatives trading system. This is my attempt at building a derivatives trading system. In this first post I am going to outline the goals of the project and some of the early design decisions.
A validation tool for excel files. Sometimes you need to export data from one system for loading into another. For instance you may export a report from a derivatives trading system for information for a collateral …
Google have just released their speech API. One really cool feature is the ability to transcribe voice in real time. Two years ago I built an app with this idea in mind. At that at the time I could no make it work. Now …
This is another simple android application. It does one thing It keeps your phone awake.
This is a really simple android application. It does one thing It takes a photo of a web site and allows you to share the photo.
This is a script I use in my android projects to generate different sized images. You can find the script here process.vbs So I build all my images in inkscape. This is brilliant application. You can find some brilliant …
This is a very simple log class I reuse in my projects It is a hybrid of Timber by Jake Wharton and the Log in Android Universal Image Loader by Sergey Tarasevich
I think that this tool is the best search tool for windows. Everything
This is a wrapper around the Android SharedPreferences It adds a few useful extensions
In this post I am going to share some of the tools I currently use to build the blog.
In this project I am building a file explorer library for android. As I was working on catcher it became obvious I would need a file picker and explorer solution. So I did a bit of looking on the web. I found three …
This is an android application to transfer files from your phone to somewhere else. I will be built as a PC solution but can be used for a server solution also.
🧠 SECTION 14: The Council of You There are moments where you don’t need data. You need to talk. To think something through. To vent. To get perspective when your own thoughts feel stuck or circular. But Parkinson’s …
AI Is the Interface: The Future of Human-Technology Interaction Technology is the bridge that transforms data into knowledge. In the coming years, artificial intelligence will evolve from being a tool that assists humans …
Table of Contents Introduction to LLM Agents Methodologies and Core Patterns Construction - Building the Agent Collaboration - Multi-Agent Systems and Interaction Introspection, Memory, and Interpretability Applications …