How Claude works: LLMs, alignment, interpretability, agents
11 steps · about 7 h 30 min · Intermediate
- Large Language Models explained briefly (video, 3Blue1Brown, 8 min)
A short, visual picture of next-word prediction, pretraining and chatbots gives you the base for everything after it.
- Transformers, the tech behind LLMs | Deep Learning Chapter 5 (video, 3Blue1Brown, 27 min)
This shows how data flows through a transformer, which you need before reading about training or interpretability.
- Anthropic's Prompt Engineering Interactive Tutorial (interactive, Anthropic (GitHub), 2 h)
Hands-on exercises show you how a model responds to instructions, so you learn its behaviour by using it.
- Prompt engineering overview (doc, Claude Platform Docs, 15 min)
It adds the current official guidance, including defining success criteria and testing prompts.
- Claude's constitution (article, Anthropic, 15 min)
A plain-language overview of Constitutional AI, the idea of training a model on written principles.
- Constitutional AI: Harmlessness from AI Feedback (article, arXiv (Bai et al., Anthropic), 1 h)
The original paper covers self-critique, revision and reinforcement learning from AI feedback (RLAIF). Skim the method sections after the overview.
- Building effective agents (article, Anthropic, 25 min)
This turns the model into systems: workflows versus agents, and why simple, composable patterns tend to win.
- Writing effective tools for agents — with agents (article, Anthropic Engineering, 25 min)
It shows how tool design and evaluation decide whether an agent works.
- Tracing the thoughts of a large language model (article, Anthropic, 20 min)
A readable tour of what interpretability research has found inside a model, such as planning ahead and shared concepts across languages.
- Open-sourcing circuit-tracing tools (interactive, Anthropic, 45 min)
You can generate and explore attribution graphs on open-weights models yourself instead of only reading about them.
- Transformer Circuits Thread (reference, Anthropic Interpretability team, 1 h 30 min)
The primary research papers, including Towards Monosemanticity and Scaling Monosemanticity, are the final step for going deeper.