Pages without language links
The following pages do not link to other language versions.
Showing below up to 100 results in range #51 to #150.
View (previous 100 | next 100) (20 | 50 | 100 | 250 | 500)
- Comparison of sexually transmitted diseases
- Comparison of terms related to agency
- Competence gap
- Content sharing between AIs
- Continually make new cards
- Continuous takeoff
- Convergent evolution of values
- Corrigibility
- Corrigibility may be undesirable
- Counterfactual of dropping a seed AI into a world without other capable AI
- Creative forgetting
- Credit card research 2021
- Dealing with bad problems in spaced proof review
- Debates shift bystanders' beliefs
- Deck options for proof cards
- Deck options for small cards
- Deconfusion
- Definitions last
- Deliberate practice for learning proof-based math
- Depictions of learning in The Blue Lagoon are awful
- Desiderata for dissolving the question
- Different mental representations of mathematical objects is a blocker for an exploratory medium of math
- Different senses of claims about AGI
- Difficulty of AI alignment
- Discontinuities in usefulness of whole brain emulation technology
- Discovery fiction
- Discursive texts are difficult to ankify
- Distillation is not enough
- Do an empty review of proof cards immediately after adding to prevent backlog
- Doomer argument against AI safety
- Dual ratings for spaced inbox
- Duolingo
- Duolingo does repetition at the lesson level
- Duolingo for math
- Emotional difficulties of AI safety research
- Emotional difficulties of spaced repetition
- Empty review
- Encoding dependence problem
- Equivalence classes of prompts
- Evolution
- Exhaustive quizzing allows impatient learners to skip the reading
- Existential win
- Existing implementations of card sharing have nontrivial overhead
- Expert response heuristic for prompt writing
- Explanation science
- Explorable explanation
- Explosive aftermath
- Fake motivation
- Feeling like a perpetual student in a subject due to spaced repetition
- Feynman technique fails when existing explanations are bad
- Finding the right primitives for spaced repetition responses
- Finiteness assumption in explorable media
- Flag things to fix during review
- Fractally misfit
- Fractional progress argument for AI timelines
- Future planning
- Giving advice in response to generic questions is difficult but important
- Goalpost for usefulness of HRAD work
- HCH
- Hardware-driven vs software-driven progress
- Hardware argument for AI timelines
- Hardware overhang
- Highly reliable agent designs
- Hnous927
- How doomed are ML safety approaches?
- How meta should AI safety be?
- How similar are human brains to chimpanzee brains?
- Human safety problem
- Hyperbolic growth
- If you want to succeed in the video games industry
- Ignore Anki add-ons to focus on fundamentals
- Importance of knowing about AI takeoff
- Improvement curve for good people
- Incremental reading
- Incremental reading in Anki
- Instruction manuals vs giving the answers
- Integration card
- Intelligence amplification
- Inter-personal comparison test
- Interacting with copies of myself
- Interaction reversal between knowledge-to-be-memorized and ideas-to-be-developed
- Intra-personal comparison test
- Is AI safety no longer a scenius?
- It is difficult to find people to bounce ideas off of
- It is difficult to get feedback on published work
- Iterated amplification
- Iteration cadence for spaced repetition experiments
- Jelly no Puzzle
- Jessica Taylor
- Jonathan Blow
- Kanzi
- Kasparov window
- Laplace's rule of succession argument for AI timelines
- Large graduating interval as a way to prevent pattern-matching
- Large graduating interval as substitute for putting effort into making atomic cards
- Late 2021 MIRI conversations
- Late singularity
- Learning-complete
- Linked list proof card
- List of AI safety projects I could work on