Skip to content

Home/Blog/Language & meaning

Language & meaning

21 articles

July 21, 2026 How a sentence becomes an answer: an LLM end to end Most explanations of large language models cover one piece, attention, or tokens, or sampling, in isolation. This follows a single sentence all the way through the machine, from the moment… July 20, 2026 Prompt engineering in 2026: what still works and what changed If your prompts still open with "act as an expert" and "let's think step by step," you're using 2023 advice on 2026… July 18, 2026 How AI generates images: from noise to a picture Type a sentence, get an image that never existed. The technology behind it, diffusion, is one of the most simple ideas in… July 13, 2026 How to read a model release Every few weeks a lab announces a new frontier model and every headline says the same thing. Here's how to work out what… July 13, 2026 Why AI answers the question you asked, not the one you meant Ask a model whether it can do something and it may tell you rather than doing it. The gap between literal meaning and… July 11, 2026 How AI generates video: from noise to motion Text-to-video went from a novelty to convincing minute-long clips with synchronised audio in about two years. The… July 11, 2026 Why AI thinks hot and cold mean the same thing Word embeddings score "accept" and "reject" at 0.73 similarity. The reason is the idea embeddings are built on, and it… July 8, 2026 Context engineering: the skill that replaced prompt engineering Prompt engineering didn't die, it got absorbed. The bottleneck moved from how you phrase a request to what information… July 7, 2026 How reasoning models work: AI that thinks before answering In 2025 a new kind of model arrived: one that pauses to think, working through a problem on internal scratch paper before… July 4, 2026 Why AI hallucinates: the confident lie is a feature, not a bug AI models don't hallucinate because they're broken. They hallucinate because we trained and scored them in a way that… June 26, 2026 How transformers work: the architecture that ate AI One 2017 paper replaced the entire previous approach to sequence modeling and made modern AI possible. Here's what a… June 25, 2026 Why AI gives different answers: sampling and temperature Ask a chatbot the same question twice and you often get two different answers. That is not a glitch. A language model does… June 22, 2026 What is multimodal AI? One model that sees, reads, and hears For years, AI was single-track, one model read text, another saw images, a third heard audio. Multimodal AI collapses… June 21, 2026 What is a context window? Why bigger isn't better Every model launch brags about a bigger context window, now measured in millions of tokens. The part the marketing leaves… June 18, 2026 What is a token? How AI reads text in chunks Ask a model how many r's are in "strawberry" and it often says two. The answer is three. It is not bad at counting; it… June 17, 2026 Who said that? Why diarization is harder than transcription Transcription answers what was said. Diarization answers who said it, and on real-world audio the error rate is still… June 13, 2026 Why AI works worse in your language The gap between English and everything else is not about linguistic difficulty. It is about training data share, tokenizer… June 11, 2026 What is a large language model (LLM)? Complete guide Large language models are the systems behind ChatGPT, Claude, and Gemini, the technology that made AI feel like it could… June 6, 2026 What is natural language processing (NLP)? Every search, translation, voice assistant, and chatbot runs on natural language processing, the field of getting… June 1, 2026 Why long context windows fail: the lost-in-the-middle problem Models now advertise context windows of a million tokens, and they pass the standard needle-in-a-haystack test almost… May 24, 2026 How to reduce AI hallucinations: what actually works You cannot instruct a model into being truthful, because the process that invents a fact is the same one that recalls a…

Other subjects

Foundations 27 Theory, history and the parts that will still be true in twenty years. Agents 11 Building agents, deploying them, and why most attempts do not reach production. Evaluation & evidence 12 Measurement, benchmarks, and how to tell whether a claim is worth anything. Building with AI 18 Retrieval, cost, infrastructure and the practical business of shipping something. Safety & governance 11 Alignment, security, regulation and who is accountable when it goes wrong.