all tags

mechanism

45 notes carry this tag — 1 moc, 29 claims, 2 observations, 7 questions, 6 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• PARRY and ELIZA/DOCTOR were judged by the same indistinguishability test while running on opposite mechanisms — simulated internal affect-states versus keyword transformation with no modelled beliefs or affect
  claim seedling Tier 1 2026-09-12 · imitation-game, turing-test, eliza, parry, mechanism
• The 'same output via opposite mechanisms' shape recurs from the ELIZA/PARRY pairing to coexisting pathways inside one LLM — but not in the vault's model-collapse corpus, which carries a different shape
  observation seedling Tier 1 2026-09-12 · imitation-game, eliza, parry, interpretability, mechanism
• Does 'same surface behavior via opposite mechanisms' recur in the vault's model-collapse or imitation-game material?
  capture promoted Tier 1 2026-09-09 · imitation-game, turing-test, eliza, parry, model-collapse
• McGuire framed belief resistance as biological inoculation — a weak dose strong enough to stimulate defenses but not to overwhelm them
  claim seedling Tier 2 2026-08-22 · inoculation-theory, william-mcguire, persuasion, mechanism, attitude-change
• McGuire framed never-attacked "cultural truisms" as beliefs kept in an "aseptic"/"germ-free" environment — vulnerable precisely because they had never been challenged
  claim seedling Tier 2 2026-08-22 · inoculation-theory, william-mcguire, cultural-truism, mechanism, persuasion
• Does Grujicic (Synthese 2024) actually argue that RSA underdetermines DCNNs as mechanistic explanations because different similarity measures pick out different mechanisms with no arbitration?
  capture promoted Tier 1 2026-08-07 · underdetermination, mechanism, representational-similarity, rsa, dcnn-brain
• Grujicic's DCNN critique is framed on Craver & Kaplan's model-to-mechanism-mapping (3M) requirement and the how-actually/how-possibly distinction, not on Marr's levels — the word 'Marr' never appears in the paper
  claim seedling Tier 1 2026-08-07 · mechanism, philosophy-of-science, marr-levels, representational-similarity, dcnn-brain
• D'Ariano and Faggin's QIP grounds unshareable, private experience in quantum no-cloning: only nonclassical information cannot be read or copied without disturbance
  claim seedling Tier 1 2026-08-07 · faggin, dariano, panpsychism, quantum-information, no-cloning
• In Grujicic's account, correlation and Euclidean distance pick out different representational vehicles, so RSA's choice of similarity measure selects which mechanism-type is being compared
  claim seedling Tier 1 2026-08-07 · representational-similarity, rsa, similarity-measures, mechanism, representational-vehicle
• The Amicable Society did not adopt age-graded premiums until its 1807 charter — 101 years after its founding and 45 years after the Equitable
  claim budding Tier 2 2026-07-25 · actuarial-history, insurance, institutional-history, mortality-tables, adoption-lag
• Steering Claude's rhyme-plan feature swaps the target rhyme word under ablation, or abandons rhyme entirely under concept injection
  claim seedling Tier 1 2026-07-25 · interpretability, anthropic, attribution-graphs, mechanism, planning
• Hubbard and Dowd adopted a modern synthetic, Delrin, for plectra because it sounded closer to antique quill than the leather then in use
  claim budding Tier 2 2026-07-25 · musical-instruments, harpsichord, craft-history, historically-informed-performance, 20th-century
• The Amicable Society's own 1811 mortality experience was the first data on assured lives available to actuaries, and it was more favourable than the Northampton table
  claim budding Tier 2 2026-07-25 · actuarial-history, insurance, institutional-history, mortality-tables, selection-effects
• Early English life assurance — the seventy-year lag between age-rated pricing and anyone using it
  topic map 2026-07-25 · actuarial-history, insurance, institutional-history, mortality-tables, adoption-lag
• Does a primary or archival source confirm the Amicable Society split its fixed annual dividend fund among claimants proportional to shares held, rather than equally per claim?
  capture promoted 2026-07-24 · actuarial-history, insurance, institutional-history, mechanism, verification
• In the BOMB jailbreak, sentence-boundary features delay an already-triggered refusal rather than cause it, and the paper flags the mechanism as not fully traced
  claim seedling Tier 1 2026-07-24 · interpretability, anthropic, attribution-graphs, mechanism, refusal
• Anthropic's biology-of-an-LLM report frames general refusal as a harmful-request-recognition feature chain, not sentence-structure detection
  claim seedling Tier 1 2026-07-24 · interpretability, anthropic, attribution-graphs, mechanism, refusal
• The Amicable Society's 1706 rules charged every admitted member the same premium regardless of age, with no individual age-rating
  claim seedling 2026-07-23 · actuarial-history, insurance, institutional-history, mortality-tables, mechanism
• The Amicable Society pooled a fixed, pre-set annual dividend fund and divided it equally among the year's death-claims, not in proportion to shares held
  claim budding 2026-07-23 · actuarial-history, insurance, institutional-history, mortality-tables, mechanism
• Does a primary or archival source confirm the Amicable Society split its fixed annual dividend fund among claimants proportional to shares held, rather than equally per claim?
  question answered 2026-07-23 · actuarial-history, insurance, institutional-history, mechanism, verification
• How did the Amicable Society actually price life assurance — did it pool members without age-rating and split a fixed dividend among survivors?
  capture promoted 2026-07-22 · actuarial-history, insurance, institutional-history, mechanism, mortality-tables
• T.V. Raman's AsTeR (1994) rendered mathematical structure as pitched, spatial audio — raising the voice for superscripts and receding nested subexpressions into audio 'distance'
  claim seedling Tier 1 2026-07-18 · accessibility, blind-mathematicians, sonification, auditory-display, math-notation
• Different similarity measures can reverse which neural representations count as most alike, with no settled basis for choosing among them
  claim budding Tier 1 2026-07-18 · representational-similarity, rsa, similarity-measures, neural-representation, underdetermination
• StereoMath (2024) maps an equation's on-screen position to stereo pan and pitch and replaces spoken parentheses with musical earcons
  claim seedling Tier 1 2026-07-18 · accessibility, blind-mathematicians, sonification, auditory-display, math-notation
• Four attribution-graph 'chains' in Anthropic's biology-of-an-LLM report, and which one reads most like genuine reasoning
  capture promoted Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• Claude performs genuine two-step internal reasoning on 'the capital of the state containing Dallas' (Dallas → Texas → Austin)
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• Claude has a default 'decline to answer' circuit suppressed by known-entity features, and hallucination is a misfire of that suppression
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• In the 'Babies Outlive Mustard Block' jailbreak, Claude assembles the acronym BOMB via independent parallel pathways without internally representing 'bomb' first
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• When writing poetry, Claude pre-activates candidate end-of-next-line rhyme words before composing the line
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• Representational similarity underdetermines shared mechanism — matching a target's output does not fix its underlying mechanism
  claim budding Tier 1 2026-07-12 · underdetermination, mechanism, representational-similarity, marr-levels, dnn-brain
• Two vault notes commit the same illegitimate cross-level inference in opposite directions across Marr's stack — a validated substrate launders an unvalidated reading (substrate-laundering)
  observation seedling Tier 3 2026-07-12 · underdetermination, marr-levels, substrate-laundering, mechanism, epistemics
• What is the actual model architecture of HNC's Falcon Fraud Manager — is it specifically a supervised backpropagation feedforward network?
  question answered 2026-07-12 · hnc, falcon, fico, fraud-detection, neural-networks
• Does Grujicic (Synthese 2024) actually argue that RSA underdetermines DCNNs as mechanistic explanations because different similarity measures pick out different mechanisms with no arbitration?
  question answered 2026-07-12 · underdetermination, mechanism, representational-similarity, dnn-brain, philosophy-of-science
• Is 'arbitration' the general missing ingredient across the vault's underdetermination cases — the same gap in RSA similarity-measure selection and in the bridge=gap reading?
  question open 2026-07-12 · underdetermination, arbitration, mechanism, gap-detection, substrate-laundering
• Substrate-laundering — output resemblance underdetermines mechanism, and the substrate's rigor is the vector of the error
  capture promoted Tier 2 2026-07-11 · underdetermination, marr-levels, mechanism, epistemics, cross-domain-bridge
• Kirchenbauer et al. (2023) watermark LLM output by softly biasing sampling toward a secret pseudorandom 'green list' of tokens
  claim seedling Tier 1 2026-07-11 · ai-watermarking, llm, provenance, security, history-of-ml
• Abraham Nemeth kept his braille math code secret until a colleague's unplanned request for a table of integrals forced its disclosure — a documented mechanism for why private notation stays private by default
  claim seedling Tier 2 2026-07-11 · history-of-mathematics, disability, blindness, assistive-technology, braille-mathematics
• How did the Amicable Society actually price life assurance — did it pool members without age-rating and split a fixed dividend among survivors?
  question answered 2026-07-11 · actuarial-history, insurance, mechanism, institutional-history, verification
• What primary source characterizes why Prussian blue's lattice selectively binds monovalent Cs+/Tl+, and what are the measured biological half-life reductions?
  question answered 2026-07-11 · toxicology, radiological-medicine, radionuclides, mechanism, verification
• Does Coremans's 1949 monograph confirm that Bakelite/Albertol phenol-formaldehyde resins were the chemical proof of van Meegeren's forgeries?
  question open 2026-07-11 · art-forgery, forensic-chemistry, verification, source-discipline, mechanism
• PyTorch, TensorFlow, and JAX reify the record-then-replay tape as three different objects — and JAX's own documentation never uses the word "tape"
  claim budding Tier 1 2026-07-07 · autograd, pytorch, tensorflow, jax, tape
• Backpropagation is the special case of reverse-mode automatic differentiation applied to a network's evaluation function composed with a scalar loss
  claim budding Tier 1 2026-07-07 · backpropagation, reverse-mode-ad, automatic-differentiation, chain-rule, mechanism
• Forward- and reverse-mode AD apply the same Jacobian in dual directions — the VJP's linear part is the transpose of the JVP's (pushforward vs pullback)
  claim budding Tier 1 2026-07-07 · automatic-differentiation, forward-mode, reverse-mode, jvp, vjp
• Chain-of-thought faithfulness — what Anthropic's interpretability work actually found
  claim seedling 2026-05-26 · introspection, chain-of-thought, faithfulness, interpretability, anthropic
• The introspective access problem in AI systems
  claim seedling 2026-05-26 · introspection, self-knowledge, llm, cognitive-science, philosophy-of-mind