Conditioning Generative Models for Alignment
📖 Description
*This post was written under Evan Hubinger's direct guidance and mentorship, as a part of the*[*Stanford Existential Risks Institute ML Alignment Theory Scholars (MATS) program*](https://www.lesswrong.com/posts/8vLvpxzpc6ntfBWNo/seri-ml-alignment-theory-scholars-program-2022)*. It builds on work done on simulator theory by Janus, who came up with the strategy this post aims to analyze; I'm also grateful to them for their comments and their mentorship during the AI Safety Camp, to Johannes Treutlein for his feedback and helpful discussion, and to Paul Colognese for his thoughts.*
📊 Game Impacts
| Variable | Change | Condition |
|---|---|---|
| Research | +10 | Always |
| Vibey Doom | +5 | Always |
| Ethics Risk | -5 | Always |
💭 Reactions
🔬 Safety Researcher Reaction:
⚠️ Placeholder - Needs Real Quote
"Critical insights for the field"
"Critical insights for the field"
📰 Media Reaction:
⚠️ Placeholder - Needs Real Quote
"Discussed in AI safety community"
💡 Found a Real Quote? Suggest it here
"Discussed in AI safety community"
🤝 Found an Issue?
This event data is sourced from the pdoom-data repository. If you notice errors or want to suggest improvements:
GitHub Issue (Preferred) 📧 Email (No GitHub)