# Seed

> Seed: The starting value of a random number generator. The same seed and settings reproduce the same samples on the same setup.

Canonical: https://llmdojo.dev/glossary/seed

Also called seeds.

The starting value of a random number generator. The same seed and settings reproduce the same samples on the same setup.

Learn it in the lesson: [Seeds and determinism](https://llmdojo.dev/learn/model-foundations/sampling/seeds-and-determinism) (Model Foundations · Next-Token Prediction and Sampling).

## Interview questions about Seed

- [Compare PCA and autoencoders as ways to fight the curse of dimensionality, and explain how you'd tell which compression helps downstream.](https://llmdojo.dev/interview/q/compare-pca-and-autoencoders-as-ways-to-fight-the-curse-of-dimensionality)
- [Implement a local training pipeline for a text-embedding recommender built from member profiles, item text and click or skip interactions, with leakage-resistant splits and reproducible inference.](https://llmdojo.dev/interview/q/implement-a-local-training-pipeline-for-a-text-embedding-recommender-built-from)
- [Your integration tests call a hosted model at temperature 0 and compare the output with an exact string. They fail now and then. What's going on, and what do you change?](https://llmdojo.dev/interview/q/your-integration-tests-call-a-hosted-model-at-temperature-0-and-compare)
- [Your LLM gives different answers to the same input. How would you make inference reproducible, and how many repeated runs would you need for a stable score?](https://llmdojo.dev/interview/q/your-llm-gives-different-answers-to-the-same-input-how-would-you)
- [Build a lightweight evaluation harness for a model served through Ollama: run a dataset of prompts, score the answers against references and report the results.](https://llmdojo.dev/interview/q/build-a-lightweight-evaluation-harness-for-a-model-served-through-ollama-run)
- [You're handed a noisy dataset for LLM post-training. How do you decide whether it helps, and what evidence would you show?](https://llmdojo.dev/interview/q/you-re-handed-a-noisy-dataset-for-llm-post-training-how-do)
- [Build a pipeline that finds math documents in web crawls and scores their quality.](https://llmdojo.dev/interview/q/build-a-pipeline-that-finds-math-documents-in-web-crawls-and-scores)
- [Implement K-means with Lloyd's algorithm. What does it optimise, how do you initialise it, and what do you do when inference data doesn't look like training data?](https://llmdojo.dev/interview/q/implement-k-means-with-lloyd-s-algorithm-what-does-it-optimise-how)

## Related
- [Logit](https://llmdojo.dev/glossary/logit)
- [LM head](https://llmdojo.dev/glossary/lm-head)
- [Autoregressive generation](https://llmdojo.dev/glossary/autoregressive)
- [Greedy decoding](https://llmdojo.dev/glossary/greedy-decoding)
- [Temperature](https://llmdojo.dev/glossary/temperature)
- [Top-k](https://llmdojo.dev/glossary/top-k)
- [Top-p (nucleus sampling)](https://llmdojo.dev/glossary/top-p)
- [Logprob](https://llmdojo.dev/glossary/logprob)
- [Glossary of every term](https://llmdojo.dev/glossary)