AISafety.md (632B)
1 2 Links to AI Safety Notes 3 4 ## Questions To Answer 5 6 What problems are falsifiable and consequently worth working on? 7 8 Is destruction of lower beings a convergent goal? 9 10 How might we solve the stop button paradox? 11 12 How to define AGI? 13 14 How to test for AGI? 15 16 #### Superintelligence - Nick Bostrom 17 18 Ch. 1 19 * [Singularity](Singularity.md) 20 * [Intelligence Explosion](IntelligenceExplosion.md) 21 * [Prognosticator](Prognosticator.md) 22 * [Optimal Bayesian Agent](OptimalBayesianAgent.md) 23 * [Flash Crash](FlashCrash.md) - Real world example of mis-specified utility function causing consequences 24 * [Strong AI](StrongAI.md) 25 * [Weak AI](WeakAI.md)