AGI safety from first principles: Superintelligence
📖 Description
In order to understand superintelligence, we should first characterise what we mean by intelligence. We can start with Legg's well-known definition, which identifies intelligence as [the ability to do well on a broad range of cognitive tasks](https://arxiv.org/abs/0712.3329).[[1]](#fn-fY9S4v85NDnW9simo-1) The key distinction I'll draw in this section is between agents that understand how to do well at many tasks because they have been specifically optimised for each task (which I'll call the task-based approach to AI), versus agents which can understand new tasks with little or no task-specific training, by generalising from previous experience (the generalisation-based approach).
📊 Game Impacts
| Variable | Change | Condition |
|---|---|---|
| Research | +10 | Always |
| Vibey Doom | +5 | Always |
| Ethics Risk | -5 | Always |
💭 Reactions
"Important work advancing our understanding of AI safety"
"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)