Ben Pace | v2.18.0Jul 31st 2020 | (+476) | ||
Ruben Bloom | v2.17.0Jul 28th 2020 | |||
Ruben Bloom | v2.16.0Jul 28th 2020 | |||
Ruben Bloom | v2.15.0Jul 28th 2020 | (+537/-108) Copy table from tag portal | ||
Kaj Sotala | v2.14.0Jul 12th 2020 | (+30) | ||
Ben Pace | v2.13.0Jul 9th 2020 | |||
Ben Pace | v2.12.0Jul 9th 2020 | (+9) | ||
Ben Pace | v2.11.0Jul 9th 2020 | (+10/-4) | ||
Ben Pace | v2.10.0Jul 9th 2020 | (+61/-31) | ||
Jim Babcock | v2.9.0Jul 8th 2020 | (+287/-187) |
AI Alignment
There are narrow conceptions of alignment, where you’re trying to get it to do something like cure Alzheimer’s disease without destroying the rest of the world. And there’s much more ambitious notions of alignment, where you’re trying to get it to do the right thing and achieve a happy intergalactic civilization.
But both the narrow and the ambitious alignment have in common that you’re trying to have the AI do that thing rather than making a lot of paperclips.
|
AIXI
Corrigibility
Decision Theory
Embedded Agency
Fixed Point Theorems
Goodhart's Law
Inner Alignment
Instrumental Convergence
Logical Induction
Mesa-Optimization
Myopia
Newcomb's Problem
Optimization
Orthogonality Thesis
Outer Alignment
Solomonoff Induction
Utility Functions
Engineering Alignment
AI Boxing (Containment)AI Safety via Debate
Factored CognitionMesa-OptimizationHumans Consulting HCHOrthogonality ThesisImpact Measures
Iterated Amplification
Value Learning
Strategy
Utility FunctionsAI ProgressInstrumental ConvergenceAI RiskGPTAI Services (CAIS)
AI Takeoff
AI Timelines
Other
Centre for Human-Compatible AI
Future of Humanity Institute
GPT
Machine Intelligence Research Institute
OpenAI
Ought
Research Agendas
Artificial Intelligence is the study of creating intelligence in algorithms. On LessWrong, the primary focus of AI discussion is to ensure that as humanity builds increasingly powerful AI systems, the outcome will be good. The central concern is that a powerful enough AI, if not designed and implemented with sufficient understanding, would optimize something unintended by its creators and pose an existential threat to the future of humanity. This is known as the AI alignment problem.
Artificial Intelligence is the study of intelligence in algorithms. On LessWrong, the primary focus of thisAI discussion is to ensure that as humanity builds increasingly powerful AI systems, the outcome will be good. The central concern is that a powerful enough AI, if not designed and implemented with sufficient understanding, would optimize something unintended by its creators and pose an existential threat to the future of humanity. This is known as the AI alignment problem.
Artificial Intelligence is the study of intelligence in algorithms. On LessWrong, the focus of this discussion of AI is focused on AI Alignment, to ensure that as humanity builds increasingly powerful AI systems, the outcome will be good. The central concern is that a powerful enough AI, if not designed and implemented with sufficient understanding, would optimize something unintended by its creators and pose an existential threat to the future of humanity. This is known as the AI alignment problem.
AI or Artificial Intelligenceis the study and creation of intelligence in machines.algorithms. On LessWrong, discussion of AI is overwhelmingly focused on questions of howAI Alignment, to create advanced artificial intelligence whose outcomes are ensure that as humanity builds increasingly powerful AI systems, the outcome will be good. A The central concern is that unaligned AGI posesa powerful enough AI, if not designed and implemented with sufficient understanding, would optimize something unintended by its creators and pose an extreme existential riskthreat to human civilization and human values.the future of humanity.