How do you reverse the order of words in a sentence?
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
Trim extra spaces, split on whitespace into words, reverse the word list, then join with single spaces.
WHY — Strings instead of guessing?
Why interviewers care about Strings:
question about Strings.
trade-offs, and what you would actually do on a DSA project - not buzzwords.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1Trim extra spaces, split
on whitespace into words, reverse the word list, then join with single spaces.
- 2Splitting is O(n) time
and O(n) space for the tokens.
- 3An in-place reverse-the-whole-string then
reverse each word is the follow-up when the buffer is mutable.
- 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
Trim extra spaces, split on whitespace into words, reverse the word list, then join with single spaces. Splitting is O(n) time and O(n) space for the tokens.