Sequences and precise instructions
Be able to formulate a sequence of precise instructions that a machine can execute without interpretation, and identify when the order or clarity fails.
Everyday explanation
Imagine you are instructing a colleague who has never seen a coffee machine. If you say "press the start button" before you have said "fill it with water", the machine will run dry or the coffee will be water. A sequence is a list of steps in a specific order. Computers and machines follow instructions exactly as written. They do not guess. If a step is missing or out of order, the process stops or produces an incorrect result.
Intuition
For an instruction to work for a machine, three things are required:
- Precise – Use measurable values or specific actions. "Run the script" is better than "run that thing".
- In the right order – Prerequisites must be met before the next step. You cannot save a file before it is created.
- Complete – No implicit steps. The machine does not know what you are thinking. Every action must be explicit.
All programs, regardless of complexity, are fundamentally sequences of such precise instructions.
Mastery means
- Structure instructions so the outcome is correct
- Identify instructions that are missing or unclear
Sign in to do the exercises and build your mastery up.
Sources
Part of the goals (44)
- An AI service in operation
- The mathematics behind the models
- Foundations of computer science
- The developer's toolbox
- Train an agent with reward
- Explorer — discover that computers can learn from examples
- The language of mathematics in AI texts
- AI for beginners
- Build an AI service that survives production
- Systems knowledge for AI engineers
- Build a RAG system you can trust
- From blocks to Python
- Run models more cheaply: quantisation
- Understand how generative AI works
- Classical machine learning in practice
- Training neural networks for real
- Build an NLP system end to end
- Statistics for experiments
- Builder — collect data, train a model and test AI critically
- AI, ethics and society
- Language models in practice
- Data: collect, clean, document
- Computers that see and hear
- Classical ML for real
- Build a transformer from scratch
- Discoverer — build a game and train a machine
- Seeing and hearing with AI
- Image classification with convolutional networks
- Multimodal systems
- Frontier Lab — an independent research project
- AI safety in practice
- Fine-tune a model with LoRA
- AI in production
- Generative models in depth
- Evals in practice
- Build a voice interface
- Interpreting a language model
- Responsible AI in practice
- Train your first neural network
- Build an agent you can trust
- Build a memory system for an agent
- Deep reinforcement learning
- Fine-tune and run your own models
- Reproduce a paper