commit d025a46e14c753214cc04a6bba5663aaa219dc7a
parent 6bc2444cc13906cee7dfa97f9480b79c6c4c61b8
Author: Andrew <andrewlaack1@gmail.com>
Date: Wed, 23 Oct 2024 17:44:44 -0500
Took safety notes
Diffstat:
9 files changed, 66 insertions(+), 7 deletions(-)
diff --git a/AISafety.md b/AISafety.md
@@ -27,10 +27,10 @@ How to test for AGI?
#### Superintelligence - Nick Bostrom
Ch. 1
-* Singularity
-* IntelligenceExplosion
-* Prognosticator
-* OptimalBayesianAgent
-* FlashCrash - Real world example of mis-specified utility function causing consequences
-* StrongAI
-* WeakAI
+* [Singularity](Singularity.md)
+* [IntelligenceExplosion](IntelligenceExplosion.md)
+* [Prognosticator](Prognosticator.md)
+* [OptimalBayesianAgent](OptimalBayesianAgent.md)
+* [FlashCrash](FlashCrash.md) - Real world example of mis-specified utility function causing consequences
+* [StrongAI](StrongAI.md)
+* [WeakAI](WeakAI.md)
diff --git a/DiscreteMath.md b/DiscreteMath.md
@@ -170,4 +170,7 @@ Unit 9.3 (Representing Relations)
Unit 9.4 (Closures of Relations)
- TransitiveClosure
+ - ReflexiveClosure
+ - SymmetricClosure
+ - DiagonalRelation
- Closure
diff --git a/FlashCrash.md b/FlashCrash.md
@@ -0,0 +1,8 @@
+:ai: :safety:
+# Flash Crash (2010)
+
+Superintelligence - Bostrom
+
+## Notes
+
+**Definition:** The flash crash occurred in 2010 where two oppositional algorithmic traders began trading back and forth very quickly because their utility function specified they do so, but logically they should not have.
diff --git a/IntelligenceExplosion.md b/IntelligenceExplosion.md
@@ -0,0 +1,8 @@
+:ai: :safety:
+# Intelligence Explosion
+
+Superintelligence - Bostrom
+
+## Notes
+
+**Definition:** The intelligence explosion is the idea that once a system achieves human intelligence, it will then be able to recursively self improve causing an explosion in intelligence.
diff --git a/OptimalBayesianAgent.md b/OptimalBayesianAgent.md
@@ -0,0 +1,8 @@
+:ai: :safety:
+# Optimal Bayesian Agent
+
+Superintelligence - Bostrom
+
+## Notes
+
+**Definition:** An optimal bayesian agent is an agent that at all times takes the best possible action based on probabilities and expected values to maximize some utility/cost function.
diff --git a/Prognosticator.md b/Prognosticator.md
@@ -0,0 +1,8 @@
+:ai: :safety:
+# Prognosticator
+
+Superintelligence - Bostrom
+
+## Notes
+
+**Definition:** A prognosticator is someone who tells of the future.
diff --git a/Singularity.md b/Singularity.md
@@ -0,0 +1,8 @@
+:ai: :safety:
+# Singularity
+
+Superintelligence - Bostrom
+
+## Notes
+
+**Definition:** The singularity is a future point in time where tech growth becomes uncontrollable and irreversible.
diff --git a/StrongAI.md b/StrongAI.md
@@ -0,0 +1,8 @@
+:ai: :safety:
+# Strong AI
+
+Superintelligence - Bostrom
+
+## Notes
+
+**Definition:** Strong AI is an AI system that has very broad intelligence.
diff --git a/WeakAI.md b/WeakAI.md
@@ -0,0 +1,8 @@
+:ai: :safety:
+# Weak AI
+
+Superintelligence - Bostrom
+
+## Notes
+
+**Definition:** Weak AI is an AI system that has very narrow intelligence (think chess bot)
