Map the Complete LLM System and the Next Subjects
Separate base architecture, pretraining, post-training, inference, retrieval, tools, evaluation, policy, and infrastructure, then route each layer to its curriculum owner.
An LLM product is more than a decoder checkpoint. A useful system map prevents a retrieval result, safety policy, serving optimization, or post-training method from being mistaken for a base-architecture property.
Separate the Layers
| Layer | Example question | Later owner |
|---|---|---|
| base architecture | How do records mix across positions? | this subject / frontier architectures |
| pretraining data and objective | Which tokens and targets shaped the base model? | language-model training and data |
| post-training | How are instructions or preferences learned? | post-training and alignment |
| inference policy | How are logits converted into outputs? | this subject / AI Engineering |
| retrieval and tools | What external evidence or actions are supplied? | retrieval and agent systems |
| evaluation | Which behavior was measured and under what conditions? | evaluation and safety |
| product policy | Which inputs or outputs are allowed? | product safety and governance |
| infrastructure | How is the model placed, batched, and served? | AI Engineering |
One product change may cross several rows. Report each changed layer.
Reconstruct the Subject Path
Language Modeling defined sequences, conditional probabilities, tokenization, objectives, and evaluation. This subject built attention, Transformer blocks, decoder-only language models, training, generation, caching, and interpretation.
The next subjects can now add depth without hiding their assumptions:
- AI Engineering: kernels, accelerators, precision, quantization, distributed training, serving, and operational measurement;
- Post-training and Alignment: instruction tuning, preference methods, reward modeling, and behavior shaping;
- Retrieval and Agents: external memory, tools, planning loops, permissions, and failure recovery;
- Multimodal Models: modality encoders, fusion, objectives, datasets, and evaluation;
- Frontier Architectures: state-space and other alternative sequence mixers;
- Evaluation, Interpretability, and Safety: stronger behavioral and causal evidence, risks, and governance.
Q1. Route a system question
A team keeps the checkpoint fixed but adds a vector database and cites sources in generated answers. Which layer changed, and which later subject owns the depth?
Select one choice, then check.
Hint
Solution
Finish with a Claim Audit
For any modern LLM claim, state the changed layer, invariant components, analytical consequence, empirical measurement, comparison baseline, source boundary, and remaining unknowns. That habit is more durable than memorizing a list of current model names.