Bibliography (13):

1. Deep reinforcement learning from human preferences

2. ​ ‘instruct-tuning LLMs’ directory

3. GPT-4 Technical Report § Limitations: Calibration

4. Towards a Human-like Open-Domain Chatbot

5. ​ ‘inner monologue (AI)’ directory

6. Creativity Has Left the Chat: The Price of Debiasing Language Models

7. Consistency-diversity-realism Pareto fronts of conditional image generative models

8. Epistemic Calibration and Searching the Space of Truth

9. https://www.anthropic.com/news/claude-2

10. Introducing the next Generation of Claude

11. Constitutional AI: Harmlessness from AI Feedback

12. Mysteries of Mode Collapse

13. Wikipedia Bibliography:

    1. Midjourney