✳flâneur — a map of the web's best reading

FLI AI Safety Research Landscape - Extended - v0.43

futureoflife.org · 170 words · saved by 1 readers

FoundationsFoundations of Rational AgencyLogical UncertaintyTheory of CounterfactualsUniversal Algorithmic IntelligenceTheory of EthicsEthical MotivationOntological ValueHuman Preference AggregationInfinite EthicsNormative UncertaintyBounded RationalityConsistent Decision MakingDecision TheoryLogical CounterfactualsOpen Source Game TheorySafer Self-ModificationVingean ReflectionAbstractly Reason About Superior AgentsReflective Induction ConfidenceLöbian ObstacleOptimal Policy PreservationSafety Technique AwarenessGoal StabilityNontransitive OptionsProjecting Behavioral BoundsComputational ComplexityVerificationFormal Software VerificationVerified Component Design ApproachesAdaptive Control TheoryVerification of Cyberphysical SystemsMaking Verification More User FriendlyAutomated Vulnerability FindingVerification of Intelligent SystemsVerification of Whole AI SystemsVerification of Machine Learning ComponentsVerification of Recursive Self-ImprovementImplementation TestingValidationAvert

FLI AI Safety Research Landscape - Extended - v0.43 FLI 2017 - Draft 0.43 FLI AI Safety Research Landscape This landscape synthesizes a variety of AI safety research agendas along with other papers in AI, machine learning, and AI safety, robustness, and beneficence research. It lays out what technical research threads can help us build more robust and beneficent AI, and describes how these many topics tie together. The content in this map is also available rendered as an academic paper . This visualization works better with larger screens as there is a lot of content, it is not ideal for mobil

Explore this link on the map →

saved by

related reading