References
International AI Safety Report 2026
Mastering the game of Go without human knowledge- Mastering the game of Go with deep neural networks and tree search
- The perceptron: a probabilistic model for information storage and organization in the brain
- Some Studies in Machine Learning Using the Game of Checkers
Natural Emergent Misalignment from Reward Hacking in Production RL
Training large language models on narrow tasks can lead to broad misalignment
When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs