Chinchilla
A research paper that presented a more correct version of scaling laws for language models, influencing people's approach to optimizing models for inference budgets and context windows.
Build a research pod on Chinchilla.
6 expert discussions. Save them all to your own pod, ask any question, get cited answers.
Common Themes
Videos Mentioning Chinchilla
Training Llama 2, 3 & 4: The Path to Open Source AGI — with Thomas Scialom of Meta AI
Latent Space
A scaling law paper that emphasized the importance of training tokens over model size, influencing LLM training strategies.
Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI
Latent Space
A scaling law model that balances training and inference costs, mentioned in the context of LLaMA's development.
Oriol Vinyals: Deep Learning and Artificial General Intelligence | Lex Fridman Podcast #306
Lex Fridman
A language-only model developed by DeepMind, also part of the animal-named model sequence, with 70 billion parameters, later reused in Flamingo.
Cursor Team: Future of Programming with AI | Lex Fridman Podcast #447
Lex Fridman
A research paper that presented a more correct version of scaling laws for language models, influencing people's approach to optimizing models for inference budgets and context windows.
Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 1: Overview, Tokenization
Stanford Online
Associated with scaling laws that balance model size and data size for a given compute budget.
Stanford CS336 Language Modeling from Scratch | Spring 2026 | Lecture 9: Scaling Laws
Stanford Online
A significant paper that challenged Kaplan's scaling predictions, suggesting smaller models with more data relative to parameters (a 20:1 token-to-parameter ratio) are more compute-optimal.