Will Capabilities Generalise More?
📖 Description
[Nate](https://www.alignmentforum.org/posts/GNhMPAWcfBCASy8e6/a-central-ai-alignment-problem-capabilities-generalization) and [Eliezer](https://www.alignmentforum.org/posts/uMQ3cqWDPHhjtiesc/agi-ruin-a-list-of-lethalities) (Lethality 21) claim that capabilities generalise further than alignment once capabilities start generalising far at all. However, they have not articulated particularly detailed arguments for why this is the case. In this post I collect the arguments for and against the position I have been able to find or generate, and develop them (with a few hours' effort). I invite you to join me in better understanding this claim and its veracity by contributing your own arguments and improving mine. *Thanks to these people for their help with writing and/or contributing arguments: Vikrant Varma, Vika Krakovna, Mary Phuong, Rory Grieg, Tim Genewein, Rohin Shah.*
📊 Game Impacts
| Variable | Change | Condition |
|---|---|---|
| Research | +5 | Always |
| Vibey Doom | +5 | Always |
| Ethics Risk | -5 | Always |
💭 Reactions
"Critical insights for the field"
"Discussed in AI safety community"
🔗 Sources
🤝 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)