- Sycophancy to subterfuge: Investigating reward tampering in language models Anthropic
Reward tampering is a specific, more troubling form of specification gaming. This is where a model has access to its own code and alters the training process itself, finding a way to “hack” the reinforcement system to increase its reward. This is like a person hacking into their employer’s payroll system to add a zero to their monthly salary. - Language Learning Prompts Library – Google Docs
- You don’t need JavaScript for that – HTMHell
I need to remember the accordion option.