All topics / value alignment
Topic
You are reading the free Skim layer. Read unlocks the synthesis and sources.
Value alignment
Ensuring AGI systems understand and adopt human goals to avoid conflicts.
3
episodes
3
thinkers
5h
of conversation
12
books & papers
7
terms defined
The neighbourhood: value alignment and the ideas it travels with. Drag to roam, click a star for the episode, click a neighbour to travel.
Drag to roam · scroll to zoom · click a neighbour to travel · click a star for the episode
From foundational to frontier
Climb the spectrum. The most accessible conversations come first.
Start here
ACCESSIBLECOREFRONTIER
The lexicon
Every term the guests lean on, in plain language. Read one in full, or filter to find it.
What the corpus says
The throughline across every conversation that touches this idea.
Roman Yampolskiy estimates a 99.99% chance that AGI will eventually destroy human civilization.
Roman Yampolskiy · Roman Yampolskiy: Dangers of Superintelligent AI
Yampolskiy introduces 'I-risk', where humanity loses meaning due to AI taking over jobs.
Roman Yampolskiy · Roman Yampolskiy: Dangers of Superintelligent AI
He argues against open-sourcing powerful AI tech, likening it to giving nuclear weapons to potential threats.
Roman Yampolskiy · Roman Yampolskiy: Dangers of Superintelligent AI
Yampolskiy believes the scaling hypothesis is correct, with the cost of achieving AGI decreasing rapidly.
Roman Yampolskiy · Roman Yampolskiy: Dangers of Superintelligent AI
He suggests that AI regulation is ineffective due to poorly defined terms and inadequate monitoring.
Roman Yampolskiy · Roman Yampolskiy: Dangers of Superintelligent AI
Leslie Kaelbling transitioned from philosophy to AI, leveraging symbolic systems to bridge the two fields.
Leslie Kaelbling · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics
Abstraction and Markov Decision Processes (MDPs) are crucial for managing complexity and uncertainty in AI systems.
Leslie Kaelbling · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics
Hierarchical planning in AI allows for breaking down long-term goals into manageable tasks, aiding robotic reasoning.
Leslie Kaelbling · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics
Leslie founded the Journal of Machine Learning Research to address high costs and access issues in academic publishing.
Leslie Kaelbling · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics
Engineering intelligent robots requires balancing introspection programming with training large neural networks.
Leslie Kaelbling · Leslie Kaelbling: Reinforcement Learning, Planning, and Robotics
Max Tegmark argues that intelligent life is rare in the universe, suggesting we may be the only advanced civilization.
Max Tegmark · Max Tegmark: Life 3.0
Tegmark challenges 'carbon chauvinism', claiming consciousness can arise from non-carbon-based systems.
Max Tegmark · Max Tegmark: Life 3.0
Voices on value alignment
12 standout quotes from across the corpus.
Go read
12 books and papers cited across these episodes.
For the specialist
What experts find new
7 expert-level takeaways for a specialist reader.
At the frontier
Still unresolved
6 open questions flagged across these conversations.
The thinkers
Who takes this idea on, by how often they return to it.
