Skip to content

Learn

1306 pages on how language models behave at inference time, and what that costs.

Prompt engineering

Which prompting techniques actually change a model's output, which ones better models absorbed, and how to tell the difference on your own workload.

17 more in prompt engineering →

Multimodal AI: vision, audio, video

How models take in pixels, audio and frames — what that costs, where it fails, and which parts of the job still belong to a specialised tool.

17 more in multimodal ai: vision, audio, video →

Embeddings & vector search

How text becomes a vector, what nearness in that space does and does not mean, and what it costs to store and search a few hundred million of them.

17 more in embeddings & vector search →

AI agents & tool use

What an agent actually is once you strip the marketing off it: a loop, a set of tools, and a budget — plus everything that goes wrong when you run one against production.

17 more in ai agents & tool use →

Structured output & function calling

How to make a next-token predictor emit JSON your program can rely on — what each enforcement mechanism actually guarantees, and what you still have to check yourself.

17 more in structured output & function calling →

Fine-tuning & post-training

When changing a model's weights is the right answer, what each method actually costs, and the failure modes that make most fine-tunes a waste of a fortnight.

17 more in fine-tuning & post-training →

Inference, serving & latency

What actually happens when a request reaches a model server, and how to reason about latency, throughput, limits and failures instead of guessing at them.

17 more in inference, serving & latency →

Observability & LLMOps

How to see what your model calls are doing in production — what to log, how to trace it, what to alert on, and how to attribute the bill.

17 more in observability & llmops →

Hallucination & failure modes

Why a language model states false things fluently, which distinct failures the word hides, and how to detect each one in your own system rather than arguing about it.

17 more in hallucination & failure modes →

AI governance, policy & society

How the rules around AI are actually built — which institutions have real authority, how each policy instrument bites, and where the evidence is genuinely unsettled.

17 more in ai governance, policy & society →

Building reliable AI applications

The distributed-systems patterns an AI feature needs — idempotency, deadlines, breakers, queues, degradation — and the parts of each that change when the dependency is slow, non-deterministic and billed per attempt.

17 more in building reliable ai applications →

AI hardware, GPUs & compute

The arithmetic that decides what a model costs to run: memory bandwidth, VRAM, interconnect and utilisation, derived rather than benchmarked.

17 more in ai hardware, gpus & compute →

Open-weight models & local inference

What you can actually run on hardware you control, what the licence actually lets you do with it, and how to work both out from first principles rather than from folklore.

17 more in open-weight models & local inference →

AI in industry: vertical playbooks

What changes when a language model meets a specific industry: the sign-off that has to happen, the format the data arrives in, the metric that decides whether it works, and the failure that costs money.

17 more in ai in industry: vertical playbooks →

AGI, superintelligence, alignment & the long future

The arguments about where AI is going, stated at the strength their proponents state them — with the definitions pinned down, the evidence attributed, and the predictions labelled as predictions.

37 more in agi, superintelligence, alignment & the long future →

NLP fundamentals & classical tasks

The pre-2020 toolkit — tokenizing, BM25, taggers, classifiers, edit distance — and an honest account of which parts a language model has replaced and which parts still win.

17 more in nlp fundamentals & classical tasks →

Data engineering for AI

Getting documents out of the formats they arrive in and into a store you can index, update and reproduce — the part of an AI feature that is most of the work and none of the demos.

17 more in data engineering for ai →

AI product design & UX

How to design an interface around a component that is slow, non-deterministic, sometimes confidently wrong, and billed per interaction.

17 more in ai product design & ux →

Search, ranking & recommendation

How a ranked list is built, measured and defended — the evaluation mathematics, the tuning loop and the product decisions that sit on top of whatever retrieval engine you chose.

17 more in search, ranking & recommendation →

Enterprise adoption & change management

The artefacts an AI programme actually runs on — the scoring rubric, the pilot charter, the budget structure, the risk register — rather than a maturity model.

17 more in enterprise adoption & change management →

AI careers, skills & teams

What the work in this field actually consists of, what each role produces, and how to learn, hire, interview for and survive it without believing anybody's forecast.

17 more in ai careers, skills & teams →

Reading AI research

How to read a machine learning paper well enough to tell a real result from a well-presented one, and what the field's landmark papers actually say.

17 more in reading ai research →

Robotics & embodied AI

Why putting a model in a body is a different problem from putting one behind an API — the control deadline, the missing data, the simulation gap and the fact that failure is physical.

17 more in robotics & embodied ai →

AI myths, hype & media literacy

How to read a claim about AI — from a launch post, a demo or a headline — by finding the step where the evidence stops supporting the conclusion.

17 more in ai myths, hype & media literacy →

Context engineering

What occupies the model's window on this request, in what order, assembled by what code, and what gets evicted when the next thing no longer fits.

17 more in context engineering →

Shipping AI features: patterns & anti-patterns

The decisions around shipping an AI feature — what to build first, which shape works, what not to build at all, and the anti-patterns that are attractive enough to cost you a quarter.

17 more in shipping ai features: patterns & anti-patterns →

Python for AI: hands-on recipes

Twenty short Python recipes for calling, streaming, retrying, parsing, caching, testing and profiling language models, each ending in code that runs.

17 more in python for ai: hands-on recipes →

TypeScript, React and the web

Calling models from TypeScript and getting the tokens into a browser: streaming, cancellation, sanitising, auth, rate limits and the runtime limits you will hit.

17 more in typescript, react and the web →

Frameworks and SDKs

What each AI framework's core abstraction actually is, how a real project is structured around it, where the abstraction stops helping, and what it costs to leave.

17 more in frameworks and sdks →

Errors and troubleshooting

The error strings a model API actually returns, what the numbers inside them mean, and how to tell which of the causes you have before you start changing things.

17 more in errors and troubleshooting →

The maths behind AI

The twenty pieces of maths that actually appear in a working language model, each derived on the page with arithmetic you can reproduce.

18 more in the maths behind ai →

Architectures beyond the transformer

How the other neural architectures work — convolutions, recurrence, state space models, autoencoders, diffusion, splatting — and what each one traded to get what it got.

18 more in architectures beyond the transformer →

Reinforcement learning

The field behind RLHF, explained for an engineer who knows language models and has never trained an agent: policies, rewards, value, and the arithmetic underneath each.

17 more in reinforcement learning →

Diffusion and generative media

How diffusion models turn noise into an image, what every dial in a generation UI multiplies, and the arithmetic behind the GPU-seconds each picture costs.

17 more in diffusion and generative media →

Benchmarks, one at a time

What each named LLM benchmark actually contains, the exact arithmetic that turns answers into a score, and what that score does and does not license you to conclude.

17 more in benchmarks, one at a time →

Infrastructure and operations

Running AI systems that are already live: containers, Kubernetes, autoscaling, spot capacity, deploys, monitoring, runbooks and the quarterly capacity review.

17 more in infrastructure and operations →

Databases and storage for AI

Postgres, pgvector, SQLite, Redis and object storage for AI applications — real DDL, real index parameters, and the storage arithmetic worked out rather than asserted.

17 more in databases and storage for ai →

Knowledge graphs and structured knowledge

How to model, extract, resolve and query structured knowledge — with the queries that similarity search cannot answer, and the parts that break at scale.

17 more in knowledge graphs and structured knowledge →

Classical ML in production

The working practice of machine learning on tables: label definitions, leakage, calibration, thresholds and causal claims, worked with numbers.

17 more in classical ml in production →

Regulation, jurisdiction by jurisdiction

What the AI rules of each major jurisdiction actually require, which of them are in force, and the documents you need when somebody asks you to prove it.

17 more in regulation, jurisdiction by jurisdiction →

Prompt recipes and pattern library

Twenty complete, copyable prompts — one per task — each annotated line by line, with the failure it prevents and the signal that says it has stopped working.

17 more in prompt recipes and pattern library →

Edge and on-device AI

Running models on phones, laptops, single-board computers and microcontrollers, where memory, power and bundle size are hard limits rather than line items.

18 more in edge and on-device ai →

Field notes

First-hand accounts of building and running an LLM gateway, alongside the engineering procedures that came out of them.

17 more in field notes →

Learn · Multigrid