carado.moe

all posts

2022-11-22: just enough spoilers for a fire upon the deep to read a yudkowsky fanfic
2022-11-20: let's stick with the term "moral patient"
2022-11-20: CYOAs and futurism
2022-11-19: wonky but good enough alignment schemes
2022-11-19: logical vs indexical dignity
2022-11-18: "humans aren't aligned" and "human values are incoherent"
2022-11-18: generalized wireheading
2022-11-13: a safer experiment than quantum suicide
2022-11-12: fully aligned singleton as a solution to everything
2022-11-01: ★ a casual intro to AI doom and alignment
2022-10-31: publishing alignment research and infohazards
2022-10-30: love, not competition
2022-10-28: counterfactual computations in world models
2022-10-24: question-answer counterfactual intervals
2022-10-12: some simulation hypotheses
2022-10-11: outer alignment: two failure modes and past-user satisfaction
2022-10-06: confusion about alignment requirements
2022-10-03: ★ my current outlook on AI risk mitigation
2022-09-27: surprise! you want what you want
2022-09-27: existential self-determination
2022-09-16: ordering capability thresholds
2022-09-15: clippy in panpsychia
2022-09-09: ethics and anthropics of homomorphically encrypted computations
2022-09-08: AI alignment curves
2022-09-07: ethics juice and anthropic juice
2022-09-05: program searches
2022-08-21: ★ everything is okay
2022-08-20: PreDCA: vanessa kosoy's alignment protocol
2022-08-17: guiding your brain: go with your gut!
2022-08-17: carmack predictions
2022-08-17: alignment researchspace is potentially malign
2022-08-17: alignment research is very weird
2022-08-15: trading with superintelligence: a wonky proto-alignment scheme
2022-08-15: essential inequality vs functional inequivalence
2022-08-14: why my timelines are short: all roads lead to doom
2022-08-13: the foundation book
2022-08-13: goal-program bricks
2022-08-13: anthropic mindfulness
2022-08-12: what does it mean to value our survival?
2022-08-12: scopes of utopia
2022-08-12: future paths
2022-08-11: unviable moral patients
2022-08-11: the Insulated Goal-Program idea
2022-08-10: ruling out intuitions about materially acausal things
2022-08-07: quantum immortality and local deaths under X-risk
2022-08-07: probability under potential hardware failure
2022-08-04: tiling the cosmos might be unavoidable
2022-08-03: isn't it weird that we have a chance at all?
2022-07-27: an anthropics example
2022-07-02: generalized values: testing for patterns in computation
2022-06-21: recommending Hands and Cities
2022-06-18: solonomonoff induction, time penalty, the universal program, and deism
2022-06-18: generalized computation interpretability
2022-06-18: anthropic reasoning coordination
2022-06-10: where are your alignment bits?
2022-06-10: outer alignment: politics & philosophy
2022-06-10: diversity vs novelty
2022-06-10: "AI risk drone"
2022-05-29: concentric rings of illiberalism
2022-05-28: say "AI risk mitigation" not "alignment"
2022-05-28: plausible vs likely
2022-05-23: implementing the platonic realm
2022-05-22: AI boxing could be easy
2022-05-19: predictablizing ethic deduplication
2022-05-19: generalized adding reality layers
2022-05-16: smaller X-risk
2022-05-14: cognitive biases regarding the evaluation of AI risk when doing AI capabilities work
2022-05-13: ★ life refocus
2022-05-12: hope for infinite compute
2022-05-12: AI risk plans
2022-04-30: the uncertainty of 2+2=4
2022-04-30: a unit for utils
2022-04-13: finding earth in the universal program
2022-04-12: The Peerless
2022-04-10: bracing for the alignment tunnel
2022-03-30: should we implement free will?
2022-03-22: goals for emergency unaligned AI
2022-03-21: values system as test-driven development
2022-03-21: the word "syntax" in programming, linguistics and LISP
2022-03-21: making the UD and UDASSA less broken: identifying time steps
2022-03-21: are there finitely many moral patients?
2022-03-06: experience/moral patient deduplication and ethics
2022-03-04: ★ recognition
2022-03-02: do not hold on to your believed intrinsic values — follow your heart!
2022-02-23: my current pyramid of needs
2022-02-06: forking bitrate and entropy control
2022-02-04: political technology
2022-02-04: balancing utilitarianism
2022-02-03: hackable multiverse
2022-02-02: a cognitively hazardous idea
2022-01-11: uploading people for alignment purposes
2022-01-11: how timelines fall
2022-01-07: ★ questions about the cosmos and rich computations
2022-01-05: brittle physics and the nature of X-risks
2021-12-27: less quantum immortality?
2021-12-25: ★ yes room above paperclips?
2021-12-25: thinking about psi: as a more general json
2021-12-25: non-scarce compute means moral patients might not get optimized out
2021-12-25: database transactions: you guessed it, it's WASM again
2021-12-09: unoptimal superintelligence doesn't lose
2021-12-09: psi rewriting
2021-12-09: non-interfering superintelligence and remaining philosophical progress: a deterministic utopia
2021-12-09: freedom and diversity in Albion's Seed
2021-12-09: emotionally appreciating grand political visions
2021-12-05: the deobfuscation conjecture
2021-12-04: think in what ?
2021-11-21: the two-vtable problem
2021-11-21: Genuineness, Existential Selfdetermination, Satisfaction: pick 2
2021-11-20: unoptimal superintelligence loses
2021-11-20: rust & wasm, without wasm-pack
2021-11-20: no room above paperclips
2021-11-20: endiannesses
2021-11-08: psi: a universal format for structured information
2021-11-08: against AI alignment ?
2021-11-01: saving the server-side of the internet: just WASM, again
2021-10-25: lamenting nerds
2021-10-23: alignment is an optimization processes problem
2021-10-22: to wasm and back again: the essence of portable programs
2021-10-14: cosmic missing outs
2021-10-13: exact minds in an exact world
2021-10-11: meta-tracking
2021-09-12: do not form your own opinion
2021-08-31: ★ ∀V: A Utopia For Ever
2021-08-25: what happens when you die?
2021-08-23: right to death, therefore
2021-08-16: kolmogorov complexity objectivity and languagespace
2021-08-15: book recommendation: Greg Egan's Axiomatic
2021-07-25: what is value?
2021-07-21: systems and diversity
2021-07-21: culture tribes and legitimacy
2021-07-19: botched alignment and alignment awareness
2021-07-18: when in doubt, kill everyone
2021-07-18: AI alignment timeline codes
2021-07-17: AI alignment and wolfram physics
2021-07-16: universal complete
2021-07-10: estimating the amount of populated intelligence explosion timelines
2021-07-09: purposes for art
2021-06-30: we're all doomed
2021-06-29: disclosing subjectivity
2021-06-25: degrees of runtime metaprogrammability
2021-06-25: classifying computational frameworks
2021-06-20: cm21, a pixel art editor
2021-06-18: categories of knowledge representation
2021-06-16: the systematic absence of libertarian thought
2021-06-16: the persistent data structure argument against linear consciousness
2021-06-16: the many faces of chaos magick
2021-06-16: refusing to answer ≠ giving a negative answer
2021-06-16: my answer to the fermi paradox
2021-06-05: I'm creating a world simulation video game
2021-06-04: Overcoming Narratives
2021-05-16: Saving The Client-Side Web: just WASM and the DOM
2021-05-03: Video Games Needs A Platform
2021-05-03: The Unsatisfactorily Far Reach Of Property
2021-04-28: Plausible Quantum Suicide
2021-04-24: Let's not generalize over people
2021-04-24: CC_ -1
2021-04-01: Value and Earning
2021-03-31: "4=5"
2021-03-28: Cultural and Memetic Hygiene
2021-03-04: Value Crystallization
2021-03-04: Symbology for Topia
2021-03-04: Normies Are in Hell Too
2021-03-04: Growth Doesn't Care About Crises
2021-03-04: From-above vs Fine-grain diversity
2021-01-22: Communicating Clearly
2021-01-14: A canonical bit-encoding for ranged integers
2021-01-01: Non-solving ideologies
2020-12-31: Core values: Defining freedom
2020-12-29: A canonical and efficient byte-encoding for ints
2020-12-25: You are your information system
2020-12-24: CSS for pixeley images
2020-12-23: Unfair feedback loops
2020-12-22: ★ Rationalist by necessity
2020-12-21: Against Unicode
2020-12-20: Cringe as prejudice
2020-11-18: A Prototypeness Hierarchy of Realities
2020-11-15: Two Principles For Topia
2020-10-04: Word Report #2
2020-10-04: Where next for piracy ?
2020-10-04: Socialism as a conspiracy theory
2020-10-04: Real quick, on free will
2020-10-04: Gender Bootstrappism
2020-10-04: For UBI
2020-09-09: Determining core values & existential self-determination
2020-07-19: Cool linguistic purisms
2020-07-18: Progress/decline in fields
2020-06-28: Song Pairs that can be listened to together
2020-06-02: Word Report #1
2020-04-30: the Economic Compass
2020-04-27: Limiting Real Universes
2020-04-16: A Collection Of Compasses
2020-03-31: Book Review: 12 Rules For Life
2020-03-30: Topia: Layer 0
2020-03-29: the Belief In Society compass
2020-03-28: On Economics
2019-12-31: ★ KOLSITAN, a tiny video game
2019-08-27: Building The Castle vs Finding The Monolith
2019-07-28: Some post- words for the future
2019-04-11: Semantics: Primes and Universals, a book review
2019-03-26: The Last Global Era
2017-09-26: Analogpunk

carado.moe

top posts ★

all posts