Decoding Complexities

Give a small, free language model (an AI that writes text by predicting one small piece of text at a time) the start of a sentence, called the prompt : "In 1969, humans first" . Then continue it two different ways, called decoding strategies (the step where the model's guesses about what comes next get turned into actual words): greedy (always take the single likeliest next word) and beam search (keep several candidate sentences going at once, like exploring a few paths instead of betting on one). Same model, same prompt, two different endings: Greedy: In 1969, humans first used the Internet to communicate. In 2000, the Internet Beam: In 1969, humans first landed a man on the moon. In 2009, the The first one is fluent, and factually wrong. The model's own scoring (explained below) rates the whole second continuation about 950 times more likely than the first, and greedy decoding didn't find it here, because greedy decoding picks the most p...

Ask an LLM (large language model — the kind of AI behind tools like ChatGPT) the exact same question twice. Sometimes you get the exact same answer back, word for word. Other times you get two answers that take different angles on the same question, worded completely differently. Both are normal — and both come down to one setting (a parameter passed into the code — not to be confused with a model's parameters, the separate term for its internal size), hiding in plain sight in the same line of code everyone copies from a tutorial: outputs = model.generate( **inputs, max_new_tokens=40, # caps the reply at 40 tokens (word pieces) do_sample=False, ) That's a simplified version of the standard Hugging Face (a popular platform and code library for running AI models) transformers convention for generating text — the full version used for every result below pins a couple of extra settings for consistency, shown later. do_sample decides which of two en...

A support bot got asked "How many days do I have to recover a deleted file?" and handed back a chunk about refund policy instead. That's a retrieval failure — the step in a RAG (Retrieval-Augmented Generation) pipeline that finds the relevant piece of text before an LLM (Large Language Model) ever sees the question. A previous investigation traced one cause of bad retrieval back to chunking — how a document gets cut into pieces before anything gets compared. This time chunking wasn't the bug. The chunks were fine. The comparison itself still picked the wrong one. The refund-policy chunk scored 0.181 against that query. The chunk that actually explains the file-recovery window scored 0.134 . Not a rounding error. A clear, confident, wrong ranking, reproduced with seven lines of scikit-learn (a free Python library for exactly this kind of text math). Cosine similarity was doing exactly what it was designed to do. The problem was what it was being ask...

A model scores 97% accuracy in testing — the percentage of predictions it gets right on data it never trained on. You deploy it to production, and real-world accuracy drops to under 78%. Nothing crashed. Nothing was miscoded. So what actually broke? Nothing broke. The test score was measuring something that doesn't exist in the real world. This is data leakage — the quietest, most dangerous failure mode in machine learning, because it doesn't look like a failure at all. It looks like success. What Data Leakage Actually Is Data leakage is information that shouldn't be available at prediction time sneaking into training anyway. The model learns to rely on it. The test score looks great, because that same leaked information is sitting in the test set too. The moment the model is in the real world, making a prediction before that information exists, it falls apart. Isn't more information always better for a model, thou...

I asked a support bot: "What happens to my data if I downgrade my plan mid-cycle?" It answered confidently. It also answered a completely different question — about deleted file recovery windows, not downgrades. The model wasn't broken. The retrieval — the step that finds and hands over the right piece of text — was broken instead. So what caused that? Not the embedding model (the piece that turns text into comparable numbers), not the LLM (the model generating the actual answer), and not a bug in the prompt. It was broken because of a decision made before any of that — how the source document was cut into chunks. This is the failure mode nobody warns you about when you first build a RAG pipeline, because it doesn't look like a bug. It looks like the system working — just working on the wrong piece of text. The Default Everyone Reaches For Retrieval-Augmented Generation (RAG) has one job: find the relevant piece of a document, then han...

Every model — a neural network, a regression line, anything that learns from data — is really just a set of internal numbers called parameters, plus a single score called the loss that measures how wrong its current predictions are. Every parameter has a slope: nudge it up or down, and the loss changes. Stack all those slopes into one vector and you get the Gradient . It always points uphill — toward the steepest way to make the loss worse — whether you have 2 parameters or 175 billion. But knowing the uphill direction isn't the same as knowing what to do with it. The gradient only points up. So what good is that to a model trying to reach the bottom? Gradient Descent takes "here is uphill" and turns it into "here is your next step downhill." That's the whole idea. Every neural network, every regression model, every fine-tuning run learns using exactly this. The Update Rule Here is the entire algorithm, in one line: θ(...