Bibliography (26):

1. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

2. Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

3. Beyond Model Collapse: Scaling Up with Synthesized Data Requires Reinforcement

4. How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse

5. GPT-3: Language Models are Few-Shot Learners

6. Deep reinforcement learning from human preferences

7. Chinchilla: Training Compute-Optimal Large Language Models

8. Grandmaster-Level Chess Without Search

9. Towards a Human-like Open-Domain Chatbot

10. Self-distillation: Born Again Neural Networks

11. https://openai.com/o1/

12. Grandmaster level in StarCraft II using multi-agent reinforcement learning

13. ​ scaling-hypothesis#blessings-of-scale

    [Transclude the forward-link's context]

14. ​ ‘MARL’ directory

15. Diversifying AI: Towards Creative Chess with AlphaZero (AZ_db)

16. Best Practices and Lessons Learned on Synthetic Data for Language Models

17. LangChain Overview

18. Wikipedia Bibliography:

    1. Large language model

    2. Reinforcement learning

    3. Cannibalism

    4. OpenAI

    5. Transformative use

       https://en.wikipedia.org/wiki/Transformative_use

    6. Neural scaling law

       https://en.wikipedia.org/wiki/Neural_scaling_law

    7. Open source

    8. The Velveteen Rabbit

       https://en.wikipedia.org/wiki/The_Velveteen_Rabbit

    9. Margery Williams

       https://en.wikipedia.org/wiki/Margery_Williams