Where our lessons come from.
AIModelRace wrote the lessons, quizzes and guide summaries in Learn. They are not copies of any course. Below are the official docs, papers and standards that back up what they teach, so you can check any claim at the source.
We only list pages we have opened and checked. A link sits under a lesson because it supports that lesson's main points, not because the lesson repeats it word for word. Want a full course instead? See free AI courses.
Papers 38
- Attention Is All You Need ↗
Vaswani et al., 2017 · arxiv.org
Cited in: What AI actually is, How language models work, Transformers and mixture-of-experts, AI Basics quiz, LLM Internals quiz
- Language Models are Few-Shot Learners ↗
Brown et al. (OpenAI), 2020 · arxiv.org
Cited in: What AI actually is, Context and examples, Few-shot prompting and examples, Advanced Prompting quiz
- Training language models to follow instructions with human feedback ↗
Ouyang et al. (OpenAI), 2022 · arxiv.org
Cited in: How language models work, Alignment, safety and interpretability, AI Basics quiz
- Constitutional AI: Harmlessness from AI Feedback ↗
Bai et al. (Anthropic), 2022 · arxiv.org
Cited in: Alignment, safety and interpretability, AI Safety & Responsibility quiz
- A Survey on Hallucination in Large Language Models ↗
Huang et al., 2023 · arxiv.org
Cited in: Strengths, limits and hallucinations, Data analysis and spreadsheets, Research and summarising, Engineering: calculations, CAD scripting and verification, Taxes and personal finance, Legal documents, Health and medical information, Safety: prompt injection, hallucinations and verification, AI Basics quiz, AI at Work: Business & Professional quiz
- Switch Transformers: Scaling to Trillion Parameter Models ↗
Fedus, Zoph and Shazeer (Google), 2021 · arxiv.org
Cited in: Transformers and mixture-of-experts
- LoRA: Low-Rank Adaptation of Large Language Models ↗
Hu et al. (Microsoft), 2021 · arxiv.org
Cited in: Fine-tuning and distillation, LLM Internals quiz
- Distilling the Knowledge in a Neural Network ↗
Hinton, Vinyals and Dean, 2015 · arxiv.org
Cited in: Fine-tuning and distillation
- FlashAttention: Fast and Memory-Efficient Exact Attention ↗
Dao et al., 2022 · arxiv.org
Cited in: Transformers and mixture-of-experts, Inference optimisation
- Fast Inference from Transformers via Speculative Decoding ↗
Leviathan, Kalman and Matias (Google), 2022 · arxiv.org
Cited in: Inference optimisation, LLM Internals quiz
- Efficient Memory Management for LLM Serving with PagedAttention (vLLM) ↗
Kwon et al., 2023 · arxiv.org
Cited in: Inference optimisation, LLM Internals quiz
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers ↗
Frantar et al., 2022 · arxiv.org
Cited in: Inference optimisation
- Direct Preference Optimization ↗
Rafailov et al., 2023 · arxiv.org
Cited in: Alignment, safety and interpretability
- Denoising Diffusion Probabilistic Models ↗
Ho, Jain and Abbeel, 2020 · arxiv.org
Cited in: How image models work, Image & Video AI quiz
- High-Resolution Image Synthesis with Latent Diffusion Models ↗
Rombach et al., 2021 · arxiv.org
Cited in: How image models work
- Not what you've signed up for: Indirect Prompt Injection ↗
Greshake et al., 2023 · arxiv.org
Cited in: Productivity and email, Safety: prompt injection, hallucinations and verification, Safety and guardrails, Advanced Prompting quiz, AI at Work: Business & Professional quiz
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues? ↗
Jimenez et al., 2023 · arxiv.org
Cited in: Reading benchmarks without being fooled, Apps and coding agents, Evaluating agents, Coding loops: keep going until the tests pass, Benchmarks & Evals quiz
- Measuring Massive Multitask Language Understanding (MMLU) ↗
Hendrycks et al., 2020 · arxiv.org
Cited in: Reading benchmarks without being fooled
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark ↗
Rein et al., 2023 · arxiv.org
Cited in: Reading benchmarks without being fooled
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference ↗
Chiang et al. (LMSYS), 2024 · arxiv.org
Cited in: Reading benchmarks without being fooled, Benchmarks & Evals quiz
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learning ↗
Anthropic, 2023 · transformer-circuits.pub
Cited in: Alignment, safety and interpretability, AI Safety & Responsibility quiz
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks ↗
Lewis et al. (Meta), 2020 · arxiv.org
Cited in: Customer support bots, Research and summarising, RAG and grounding with sources, Retrieval-augmented generation, LLM Internals quiz
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models ↗
Wei et al. (Google), 2022 · arxiv.org
Cited in: Chain-of-thought and reasoning models
- Large Language Models are Zero-Shot Reasoners ↗
Kojima et al., 2022 · arxiv.org
Cited in: Chain-of-thought and reasoning models
- Self-Consistency Improves Chain of Thought Reasoning ↗
Wang et al. (Google), 2022 · arxiv.org
Cited in: Self-consistency and multiple samples, Advanced Prompting quiz
- Least-to-Most Prompting Enables Complex Reasoning ↗
Zhou et al. (Google), 2022 · arxiv.org
Cited in: Prompt chaining and decomposition
- Large Language Models Are Human-Level Prompt Engineers (APE) ↗
Zhou et al., 2022 · arxiv.org
Cited in: Meta-prompting and prompt templates
- Large Language Models as Optimizers (OPRO) ↗
Yang et al. (Google DeepMind), 2023 · arxiv.org
Cited in: Meta-prompting and prompt templates
- DSPy: Compiling Declarative Language Model Calls ↗
Khattab et al. (Stanford), 2023 · arxiv.org
Cited in: Meta-prompting and prompt templates
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena ↗
Zheng et al., 2023 · arxiv.org
Cited in: Testing prompts: golden sets, rubrics and judges, Evals in production, Advanced Prompting quiz
- Self-Refine: Iterative Refinement with Self-Feedback ↗
Madaan et al., 2023 · arxiv.org
Cited in: Refinement loops: generate, critique, revise, Loops, Graphs & Agents quiz
- Reflexion: Language Agents with Verbal Reinforcement Learning ↗
Shinn et al., 2023 · arxiv.org
Cited in: Refinement loops: generate, critique, revise, Coding loops: keep going until the tests pass, Loops, Graphs & Agents quiz
- ReAct: Synergizing Reasoning and Acting in Language Models ↗
Yao et al., 2022 · arxiv.org
Cited in: Agent fundamentals, Thinking in loops and graphs, Agent loops: plan, act, observe (ReAct), Loops, Graphs & Agents quiz
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models ↗
Yao et al., 2023 · arxiv.org
Cited in: Thinking in loops and graphs, Tree of Thoughts: branching and searching, Loops, Graphs & Agents quiz
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models ↗
Besta et al., 2023 · arxiv.org
Cited in: Graphs: Graph of Thoughts and agent workflow graphs, Loops, Graphs & Agents quiz
- Toolformer: Language Models Can Teach Themselves to Use Tools ↗
Schick et al. (Meta), 2023 · arxiv.org
Cited in: Tool use and function calling
- Lost in the Middle: How Language Models Use Long Contexts ↗
Liu et al., 2023 · arxiv.org
Cited in: Strengths, limits and hallucinations, Research and summarising, Context engineering, Long context, context engineering and memory, Retrieval-augmented generation, Loops, Graphs & Agents quiz
- Improving Factuality and Reasoning through Multiagent Debate ↗
Du et al., 2023 · arxiv.org
Cited in: Multi-agent patterns
Official guides 13
- Prompt engineering overview ↗
Anthropic · platform.claude.com
Cited in: Your first genuinely useful conversations, Iterating and debugging prompts, Writing, copywriting and marketing, Social media, Business plans and strategy, Productivity and email, Education and tutoring, The full prompting process
- Claude prompting best practices ↗
Anthropic · platform.claude.com
Cited in: The anatomy of a strong prompt, Context and examples, Structure and output format, Websites and web development, Game development, Engineering: calculations, CAD scripting and verification, Few-shot prompting and examples, Roles and system prompts, Structured output: JSON and schemas, Prompt chaining and decomposition, Prompting Fundamentals quiz, Build with AI: Software & Media quiz
- Building effective agents ↗
Anthropic · anthropic.com
Cited in: Apps and coding agents, Automation and workflows, Customer support bots, Prompt chaining and decomposition, Agent fundamentals, Architectures and orchestration, Thinking in loops and graphs, Loop control: stopping conditions, budgets and drift, Graphs: Graph of Thoughts and agent workflow graphs, Multi-agent patterns, AI Agents quiz
- Effective context engineering for AI agents ↗
Anthropic · anthropic.com
Cited in: Context engineering, Long context, context engineering and memory, AI Agents quiz
- Writing effective tools for agents ↗
Anthropic · anthropic.com
Cited in: Designing tools and MCP servers
- Tracing the thoughts of a large language model ↗
Anthropic · anthropic.com
Cited in: Alignment, safety and interpretability
- Prompt engineering ↗
OpenAI · developers.openai.com
Cited in: Your first genuinely useful conversations, The anatomy of a strong prompt, Writing, copywriting and marketing, Social media, Business plans and strategy, Productivity and email, Education and tutoring, The full prompting process, Roles and system prompts
- Reasoning best practices ↗
OpenAI · developers.openai.com
Cited in: Prompting reasoning models, Chain-of-thought and reasoning models, Prompting Fundamentals quiz, Advanced Prompting quiz
- Prompt design strategies ↗
Google · ai.google.dev
Cited in: Your first genuinely useful conversations, The anatomy of a strong prompt, Context and examples, Writing, copywriting and marketing, Social media, Business plans and strategy, Productivity and email, Education and tutoring
- Mixture of Experts Explained ↗
Hugging Face · huggingface.co
Cited in: Transformers and mixture-of-experts, Models & Labs quiz
- Neural networks (video series) ↗
3Blue1Brown · 3blue1brown.com
Cited in: What AI actually is, How language models work
- Google Search's guidance about AI-generated content ↗
Google Search Central · developers.google.com
Cited in: SEO and content strategy
- Creating helpful, reliable, people-first content ↗
Google Search Central · developers.google.com
Cited in: SEO and content strategy
Official docs 25
- Prompt caching ↗
Anthropic · platform.claude.com
Cited in: Cost, speed and quality, Inference optimisation, Models & Labs quiz
- Building with extended thinking ↗
Anthropic · platform.claude.com
Cited in: Prompting reasoning models, Chain-of-thought and reasoning models
- Vision ↗
Anthropic · platform.claude.com
Cited in: Prompting with images, audio and video
- Tool use overview ↗
Anthropic · platform.claude.com
Cited in: Designing tools and MCP servers, Tool use and function calling
- Define success criteria and build evaluations ↗
Anthropic · platform.claude.com
Cited in: Iterating and debugging prompts, Choosing a model for your task, The full prompting process, Testing prompts: golden sets, rubrics and judges, Evaluating agents, Evals in production, Benchmarks & Evals quiz
- Context windows ↗
Anthropic · platform.claude.com
Cited in: Strengths, limits and hallucinations
- Text generation ↗
OpenAI · developers.openai.com
Cited in: How language models work, AI Basics quiz
- Structured model outputs ↗
OpenAI · developers.openai.com
Cited in: Structure and output format, Structured output: JSON and schemas, Prompting Fundamentals quiz
- Function calling ↗
OpenAI · developers.openai.com
Cited in: Automation and workflows, Designing tools and MCP servers, Tool use and function calling
- Working with evals ↗
OpenAI · developers.openai.com
Cited in: Iterating and debugging prompts, Choosing a model for your task, Testing prompts: golden sets, rubrics and judges, Evaluating agents, Evals in production
- Images and vision ↗
OpenAI · developers.openai.com
Cited in: UI and UX design, Architecture and interior design, Prompting with images, audio and video
- Image generation ↗
OpenAI · developers.openai.com
Cited in: Image prompting that gives you control, Editing and consistent characters, Graphic design and logos, Image generation workflows
- Prompt caching ↗
OpenAI · developers.openai.com
Cited in: Cost, speed and quality, Models & Labs quiz
- Model optimization (fine-tuning) ↗
OpenAI · developers.openai.com
Cited in: Fine-tuning and distillation
- Image generation with Gemini ↗
Google · ai.google.dev
Cited in: Image prompting that gives you control, Editing and consistent characters, Graphic design and logos, Image generation workflows, Architecture and interior design, Image & Video AI quiz, Build with AI: Software & Media quiz
- Generate videos with Veo ↗
Google · ai.google.dev
Cited in: Directing AI video, Video generation workflows, Animation and motion design, Image & Video AI quiz
- Long context ↗
Google · ai.google.dev
- Audio understanding ↗
Google · ai.google.dev
Cited in: Music, audio and voice, Prompting with images, audio and video
- SynthID ↗
Google DeepMind · deepmind.google
Cited in: Rights, disclosure and responsible use
- Transformers documentation ↗
Hugging Face · huggingface.co
Cited in: Open weights vs closed models
- PEFT (parameter-efficient fine-tuning) ↗
Hugging Face · huggingface.co
Cited in: Fine-tuning and distillation
- Blender Python API documentation ↗
Blender Foundation · docs.blender.org
Cited in: 3D design, text-to-3D and Blender scripting, Build with AI: Software & Media quiz
- Godot Engine documentation ↗
Godot Engine · docs.godotengine.org
Cited in: Game development
- pandas documentation ↗
pandas · pandas.pydata.org
Cited in: Data analysis and spreadsheets
- Is my data used for model training? ↗
Anthropic Privacy Center · privacy.claude.com
Cited in: Using AI safely and responsibly, Taxes and personal finance, Legal documents, AI Safety & Responsibility quiz, AI at Work: Business & Professional quiz
Standards and policy 8
- Model Context Protocol: introduction ↗
Model Context Protocol · modelcontextprotocol.io
Cited in: Designing tools and MCP servers, AI Agents quiz
- OWASP Top 10 for LLM Applications ↗
OWASP · genai.owasp.org
Cited in: Using AI safely and responsibly, Customer support bots, Safety: prompt injection, hallucinations and verification, Safety and guardrails, AI Agents quiz
- AI Risk Management Framework ↗
NIST · nist.gov
Cited in: Using AI safely and responsibly, Safety and guardrails, AI Safety & Responsibility quiz
- Coalition for Content Provenance and Authenticity (C2PA) ↗
C2PA · c2pa.org
Cited in: Rights, disclosure and responsible use, Image & Video AI quiz
- Copyright and Artificial Intelligence ↗
U.S. Copyright Office · copyright.gov
Cited in: Rights, disclosure and responsible use, Graphic design and logos, Music, audio and voice
- AI Act: regulatory framework for AI ↗
European Commission · digital-strategy.ec.europa.eu
Cited in: Rights, disclosure and responsible use
- Ethics and governance of AI for health: guidance on large multi-modal models ↗
World Health Organization · who.int
Cited in: Health and medical information
- WCAG 2 Overview ↗
W3C WAI · w3.org
Cited in: Websites and web development, UI and UX design
Data sources 3
- AI Benchmarking Hub ↗
Epoch AI · epoch.ai
Cited in: The model landscape in late 2026, Reading benchmarks without being fooled, Benchmarks & Evals quiz
- Artificial Analysis model comparisons ↗
Artificial Analysis · artificialanalysis.ai
Cited in: The model landscape in late 2026, Cost, speed and quality, Choosing a model for your task
- OpenRouter model catalogue (prices, context windows) ↗
OpenRouter · openrouter.ai
Cited in: The model landscape in late 2026, Cost, speed and quality, Open weights vs closed models, Models & Labs quiz
Prompting guide summaries 8
Our guide summaries each condense one published prompting guide. These are the originals.
- Prompt engineering overview and Claude best practices ↗
Anthropic · platform.claude.com
- Prompt engineering and GPT model prompting guides ↗
OpenAI · developers.openai.com
- Gemini prompt design strategies ↗
Google · ai.google.dev
- Prompt engineering and P-tuning for large language models ↗
NVIDIA · developer.nvidia.com
- Effective prompts for AI: the essentials ↗
MIT Sloan · mitsloanedtech.mit.edu
- Getting started with prompts for text-based generative AI tools ↗
Harvard University IT · huit.harvard.edu
- Prompt engineering for Grok ↗
xAI · web.archive.org · archived copy; the original page has been taken down
- Llama prompting guide ↗
Meta · developer.meta.com
Spotted a claim that doesn't match its source? Email [email protected].