123 long-form pieces on architecture, training, inference, agents and safety.
The industry's defence against data poisoning was arithmetic: an attacker needs a percentage of the corpus, and a percentage of 260 billion tokens is unobtainable. In October 2025 the largest poisoning study ever run showed the r…
In 2014 a perturbation the size of one 8-bit colour step turned a 57.7 percent panda into a 99.3 percent gibbon. Twelve years, 300 million synthetic training images and more than 10^21 training FLOPs later, the best CIFAR-10 mode…
Model registries were built to version a trained artefact you own. An LLM application's behaviour comes from a hosted snapshot that retires on someone else's calendar, plus prompts, an index and tools you change weekly. The relea…
An LLM agent with a million-token window still forgets what you told it last week. Memory is not a bigger context; it is a separate system that decides what to write down, how to summarize it, and what to pull back. Here is how t…
RLHF taught a model to answer one question well. Agentic RL asks a harder thing: take fifty actions in a live environment, most of them invisible in the final reward, and still learn which ones mattered. That single change, from …
Gender Shades measured a 34.4-point error gap on 1,270 faces and moved three vendors within seven months. New York City's mandatory bias audits produced 18 posted reports from 391 employers. The difference was not auditor skill b…
An H100 advertises 989 teraflops. Generating one token from an 8B model uses roughly 0.3% of that. The gap is not a bug in your code or a missing compiler flag; it is a single ratio, FLOPs per byte moved, and almost every perform…
Over 54 days of Llama 3 405B pre-training, the job was interrupted 466 times, roughly once every three hours. At that failure rate the checkpoint interval barely matters; what decides how much of a sixteen-thousand-GPU cluster do…
In 2021 a benchmark of 18 retrieval datasets found that a scoring function from 1994 still beat most neural retrievers outside their training domain. BM25 is not a heuristic that got lucky. It is a deliberate approximation of a p…
A 2-billion-parameter model that trades blows with one ten times its size is not an accident of architecture. It is the product of a teacher pouring its full probability distribution into a student, token by token.
Retrieval-augmented generation fetches documents at query time, scores them, and hopes the retriever got it right. Cache-Augmented Generation sidesteps the entire pipeline by preloading knowledge into the model's KV-cache before …
A comprehensive, interactive study guide covering every domain of the Claude Certified Architect - Foundations (CCAF) exam. Master agentic architecture, tool design, Claude Code configuration, prompt engineering, and context mana…