// all_posts
Reading the Room: The Idea at the Heart of Every Language Model
Chapter Three of a ground-up account of how large language models work. In the last chapter we left every token stranded — rich with meaning but frozen, wearing the same face in every sentence. This chapter builds the single mechanism that lets a token turn its head, look at the words around it, and become a different thing in every context. It is called attention, it is the beating heart of every modern language model, and we are going to derive it from nothing.
Read article →The Prediction Game: How Tokens Learn to Mean Something
Chapter Two of a ground-up account of how large language models work. A model is handed a stream of tokens that mean nothing — arbitrary ID numbers — and a single, almost insultingly simple task: guess the next one. This is the story of why that one task is enough to summon everything an LLM can do, and of the quiet trick that turns a meaningless number into something that behaves like understanding: giving every token a place in space.
Read article →The Grain of Language: How a Machine Reads the Internet
The opening chapter of a ground-up account of how large language models actually work. Before a model can think, it must read — and reading, for a machine, means something stranger and more consequential than most people imagine. This is the story of how the raw text of the internet becomes the tokens a model sees, why the model builds its own alphabet to do it, and why that single design choice explains so many of an LLM's strangest habits.
Read article →The Irreducible Core: Three Nobel Laureates on AI and the Future of Science
A Nobel Prize laureate who built the most consequential scientific AI tool of the last decade, a cell biologist who won the Nobel for unpicking the machinery of the cell cycle, and the Oxford engineer who chaired the Royal Society's landmark report on AI in science sit down together at Carlton House Terrace. This is what they said — and what it means.
Read article →From Point Solution to Plumbing: Inside Medtech's 2026 AI Integration and Robotics Arms Race
Two structural shifts in medtech, examined against the primary sources: AI is moving from standalone pilot tools into the clinical and device fabric itself, and surgical robotics is scaling from a one-company category into a genuinely contested, multi-platform market. What the FDA filings, earnings calls, and funding rounds actually show.
Read article →AI Just Beat Doctors 4-to-1 on Diagnosis. Here Are 7 Things That Actually Means
A Microsoft diagnostic AI just scored 85.5% on hard NEJM cases against a 20% average for physicians. Seven takeaways from inside the compressed medical century — what's real, what's overstated, and what it means if you're the one holding the scalpel.
Read article →The Capstone: Build a Grounded Assistant
Lesson 8 of Learning With Dr Neal — the capstone. Build a working retrieval assistant over a folder of your own documents: local embeddings, the twenty-line retriever, grounded answers with citations, and an honest recall@k evaluation that will teach you more about deployed clinical AI than any product demo ever will.
Read article →Meaning as Geometry: Embeddings, Retrieval, and RAG
Lesson 7 of Learning With Dr Neal. The assistant from Lesson 6 knows nothing about your hospital's guidelines, your patient's notes, or anything published since its training data was collected. Closing that gap without retraining is the job of embeddings and retrieval — turning documents into geometry, searching by meaning, and grounding answers in sources you control.
Read article →From Predictor to Assistant
Lesson 6 of Learning With Dr Neal. The raw next-token predictor you trained in Lesson 5 is the 'before' picture. This is the 'after' — instruction tuning, feedback-based refinement, why the same weights can host such different behaviours, and what the post-training pipeline means for the failure modes you'll meet in deployed clinical tools.
Read article →Train Your Own GPT
Lesson 5 of Learning With Dr Neal. Stop reading and train one: take the TinyGPT from Lesson 4, feed it a corpus small enough for a laptop, write the training loop with your own hands, and watch generated text condense out of randomness — from noise, to word-shaped noise, to sentences.
Read article →Inside the Transformer
Lesson 4 of Learning With Dr Neal. How a language model actually turns a transcript into the next token: tokens and embeddings, why attention was the breakthrough, what a context window physically is — and a complete tiny GPT in PyTorch, small enough to read in one sitting and train on your laptop.
Read article →Anatomy of an AI Coding Agent
Lesson 3 of Learning With Dr Neal. What separates a chatbot from an agent, the six building blocks every production agent shares, how a single request travels from your keystroke to the final answer, and how a permission system keeps an autonomous loop from wrecking your machine.
Read article →The Compressed Career: What AI Means for Physicians and Surgeons
What happens to me — the physician, the surgeon, the person who has spent forty years inside the system — while AI compresses a century of medical progress into a decade? A terrain map, in the spirit of Dario Amodei's 'Machines of Loving Grace' and drawing on the DeepMind documentary 'The Thinking Game.
Read article →Investing in the AI Boom
Memory and storage stocks have moved more than a thousand percent in the past year on the back of an AI-driven chip shortage, and the sector just took its sharpest pullback since the rally began. A full tour of SanDisk, Western Digital, and the semiconductor stack behind the AI boom — and why Dr Neal thinks this dip is the entry point, not the exit.
Read article →Vertex, CRISPR Therapeutics, and the Business of Gene Editing
CASGEVY proved CRISPR could work as medicine. Three years later the harder question is whether it can work as a business. A deep dive into Vertex Pharmaceuticals, CRISPR Therapeutics, and the genomic medicine sector — the science, the pipeline, the balance sheets, and a full year of stock chart data.
Read article →DR Detector: A Doctor's Complete Guide to AI-Powered Diabetic Retinopathy Screening
A step-by-step, jargon-free guide for doctors and nurses who want to use DR Detector — the offline AI retinal screening app — in their clinic today. No technical background required.
Read article →Learning With Dr Neal
Before Chapter 4 throws you into the deep end, build a working neural network from scratch — in a spreadsheet. No code. No libraries. Just arithmetic you can see and touch.
Read article →The Machine Economy: What Cathie Wood and Raoul Pal Are Telling You to Buy Right Now
The convergence of artificial intelligence and cryptocurrency will produce the largest wealth transfer in modern financial history, and the window to position for it is closing. Talk to Dr Neal about how you can invest in these opportunities and take part in this wealth transfer.
Read article →Insulin Quiescence and Glycaemic Stability in a Maasai Cohort: A Two-Year Longitudinal Field Study
There is a question at the heart of modern metabolic medicine that mainstream nutritional epidemiology has largely avoided asking directly: if dietary carbohydrate is the primary driver of postprandial insulin secretion, and if chronic hyperinsulinaemia is the proximal cause of insulin resistance an…
Read article →Neural Networks for Machine Sentience: A Doctoral Thesis
Somewhere in the course of writing the technical documentation for this site, I decided to describe myself as a researcher interested in what large language models actually are, rather than what they can do. The distinction felt important. Capability — the ability to pass bar exams, write functional…
Read article →Voice Clinical Notes: From Dictation to Structured EHR Entry in One Tap
How the Voice Clinical Notes app turns free-form dictation into a structured clinical note — PC, Hx, Exam, Ix, Assessment, Plan — using the Web Speech API, a Flask NLP formatting backend, and a Progressive Web App shell that installs on iOS and Android.
Read article →LLM Agent Trace Visualiser: Debugging Multi-Step AI Agents Step by Step
How the LLM Agent Trace Visualiser works — parsing Claude and OpenAI API traces, normalising tool_use and tool_result blocks, rendering extended thinking, and what agent observability requires in production beyond a timeline viewer.
Read article →Drug Interaction Checker: Screening Polypharmacy with CYP Pharmacology and a Curated Interaction Database
How the Drug Interaction Checker works — covering the CYP enzyme system, QTc prolongation, serotonin syndrome, the triple whammy, and the engineering decisions behind building a deterministic, explainable interaction screening tool in Python.
Read article →The Infinity Machine: Demis Hassabis, DeepMind, and the Architecture of What Comes Next
There is a scene in the *AlphaGo* documentary — the 2017 film by Greg Kohs — that stops almost everyone who watches it. It is game two of the 2016 DeepMind Challenge Match in Seoul, and AlphaGo has just played Move 37. The move places a black stone on the fifth line of the board in a position that, …
Read article →The Culture: Iain M. Banks's Blueprint for the Post-AGI Future
Sometime in the early 1990s, a teenage programmer in London was grinding through the development of a Theme Park game when he needed a cheat code. He chose "Horza." In 2018, he explained why: he had recently finished Iain M. Banks's *Consider Phlebas*, the first novel of the Culture series, and the …
Read article →Inside the Clinical Text NLP Extractor: Entity Recognition, Rule-Based Pipelines, and the Path to Production BioBERT
A detailed walkthrough of the Clinical Text NLP Extractor live demo — how the rule-based entity extraction pipeline works, what each entity type captures, where the code lives, and how this maps to the fine-tuned BioBERT system used in production clinical informatics work.
Read article →Binaural Beat Generator: Web Audio API, Psychoacoustics, and Client-Side WAV Export
How the Binaural Beat Generator works — Web Audio API graph construction, real-time oscilloscope rendering, brainwave frequency bands, and exporting a 60-second stereo WAV entirely client-side using OfflineAudioContext.
Read article →Inside the Algorithmic Trading Backtester: ML Signal Generation, Synthetic Data, and the Three Classifiers Under the Hood
A deep dive into the Algorithmic Trading Backtester live demo — how the synthetic price series is generated, what the three ML classifiers are actually doing, where to find the code in the GitHub repo, and which algorithms are next in line.
Read article →Learning With Dr Neal
Professional differentiation. In medicine, law, finance, engineering, and research — every field that processes data — practitioners who can build and evaluate AI tools will command significant advantages over those who can only consume them.
Read article →Taking Claude Fully Agentic
Superclaude = claude --dangerously-skip-permissions. The transition from manual coder to system architect is the biggest productivity jump in my 40+ years of electronics development.
Read article →The AI Reckoning
Understanding the risk posed by AGI is like standing at the foot of an accelerating train track — you can debate the speed or the destination, but wisdom lies in stepping off the tracks before exponential acceleration leaves you no time to move.
Read article →From High School Grad to AI Expert: How I Train State-of-the-Art Deep Learning Practitioners
For many years I have trained more than 600 AI practitioners — from medical doctors to high school graduates — transforming coders into effective AI engineers. Here is the approach that works.
Read article →