What happens when input exceeds the context window?
PICTURE THIS: A SENTENCE BECOMES TOKENS
The model does not read letters like humans. It reads these pieces, then predicts the next one.
Simple meaning
The call fails, or your client must drop history, summarize, or retrieve fewer chunks.
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
people who only read docs from people who shipped.
and tied to GenAI / LLM work.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1The call fails, or
your client must drop history, summarize, or retrieve fewer chunks.
- 2Silent truncation of the
middle or the end can hide the real question.
- 3Production systems should check
token counts before sending.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
The call fails, or your client must drop history, summarize, or retrieve fewer chunks. Silent truncation of the middle or the end can hide the real question.