The model is frozen and stateless
The idea: Weights are fixed after training; no memory between calls; it confabulates.
What you'll be able to do: You can explain why a frozen model hallucinates and has a knowledge cutoff.
The problem it solves: Ask the model today's news or your private doc: it can't know.
Builds on: Predict the next word
← Distillation: a small model learns from a big one · Next: RAG: retrieval as a callback to similarity →
All lessons