all tags

ai-safety

21 notes carry this tag — 11 claims, 1 observation, 1 question, 5 captures, 3 essays. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Essays

• 
  not strong enough to overwhelm them
  essay drafting 2026-10-11 · inoculation-theory, llm-persuasion, conspiracy-belief, ai-safety, dual-use
• 
  normal accident
  essay candidate 2026-09-13 · normal-accident-theory, charles-perrow, ai-infrastructure, power-grid, sociology-of-technology
• 
  the answer desired
  essay draft 2026-07-13 · ai-safety, argumentation, toulmin, safety-case, gap-detection

Everything else

• Does AI-safety/interpretability literature have a specific name and mechanism for plausible-sounding fabricated intermediate claims — and does it explain why two independent generations converge on the same one?
  capture promoted 2026-10-31 · ai-safety, interpretability, hallucination, fabrication, correlated-errors
• LLM errors are correlated well above chance, and the correlation rises, not falls, as paired models get individually more accurate
  claim seedling Tier 1 2026-10-31 · ai-safety, correlated-errors, algorithmic-monoculture, llm-evaluation, nlp-evaluation
• Higher 'generative-process diversity' between a model pair predicts lower correlated failure, beyond semantic similarity or capability — a single, not-yet-corroborated 2026 preprint
  claim seedling Tier 1 2026-10-31 · ai-safety, correlated-errors, algorithmic-monoculture, representational-similarity, nlp-evaluation
• Divergence, not convergence, is the literature's own default outcome for an open-ended fabricated detail with no strong training-data regularity behind it
  claim seedling Tier 1 2026-10-31 · ai-safety, hallucination, fabrication, correlated-errors, nlp-evaluation
• Citation-specific 'fabricated snippets' and reasoning-specific 'bullshitting' remain separately named, unconnected mechanisms in the literature
  observation seedling Tier 1 2026-10-31 · ai-safety, interpretability, hallucination, fabrication, citation-hallucination
• Does an independent source corroborate Tieman & Markou (2026)'s 'generative-process diversity' finding?
  question open 2026-10-31 · ai-safety, correlated-errors, algorithmic-monoculture, corroboration, single-source-cap
• Has AI-safety/NLP-evaluation literature named and studied tool-access fabrication as distinct from ordinary hallucination?
  capture promoted 2026-10-21 · ai-safety, nlp-evaluation, hallucination, tool-use, fabrication
• Do Rosario, Younes & Pires (2026) define 'grounding violation' as distinct from 'factual hallucination,' and name 'parametric leakage' as the mechanism that turns an ungrounded answer into confident fabrication
  claim seedling Tier 1 2026-10-21 · rag, nlp-evaluation, hallucination, grounding, ai-safety
• Rao, Wong & Callison-Burch (2026) name 'fabricated snippets' as a citation-reliability failure mode distinct from URL hallucination, and flag it in their own words as not yet systematically studied
  claim seedling Tier 1 2026-10-21 · citation-hallucination, reference-hallucination, nlp-evaluation, source-reliability, ai-safety
• RIKER (Roig, 2026) finds grounding accuracy and fabrication resistance are empirically separable capabilities, not two faces of one hallucination score [unverified-quant]
  claim seedling Tier 1 2026-10-21 · rag, benchmark, nlp-evaluation, hallucination, grounding
• Sethi et al. (2026) name 'fabrication after tool failure' and find its trigger is structural (whether the tool's response signals failure), not lexical, topical, or instructed
  claim seedling Tier 1 2026-10-21 · ai-safety, tool-use, hallucination, fabrication, benchmark
• Does a direct read of Charles Perrow's 1984 Normal Accidents confirm Williams & Yampolskiy's summary of Normal Accident Theory?
  capture promoted Tier 4 2026-09-14 · normal-accident-theory, charles-perrow, williams-yampolskiy, ai-safety, primary-source-verification
• Charles Perrow's 1984 'Normal Accident Theory' — reached via a misattributed sociology-of-technology hook — is the unnamed framework already latent in the vault's own AI-power-grid attack claim
  capture promoted Tier 1 2026-09-13 · cross-domain-bridge, cross-time-bridge, sociology-of-technology, normal-accident-theory, ai-safety
• Perrow's 1984 Normal Accident Theory holds that any system combining tight coupling with complex interactivity will inevitably experience a system accident
  claim seedling Tier 1 2026-09-13 · normal-accident-theory, charles-perrow, sociology-of-technology, tight-coupling, ai-safety
• The RAF's Nimrod Safety Case was found by the 2009 Haddon-Cave Review to be a 'tick-box' compliance exercise, riddled with errors, ahead of a crash that killed 14 crew
  claim seedling Tier 2 2026-07-12 · AI-safety, safety-case, Nimrod, Haddon-Cave, failure-mode
• A safety case is a structured, evidence-backed argument that a system is safe enough — long standard in nuclear/aviation/AV regulation, now proposed as the assurance backbone for frontier AI
  claim seedling Tier 1 2026-07-12 · AI-safety, safety-case, assurance, frontier-AI, argumentation
• AI safety cases inherit a 1958 argument model — and a documented failure mode
  capture promoted Tier 1 2026-07-11 · AI-safety, argumentation, Toulmin, safety-case, assurance
• The same LLM persuasion that debunks conspiracies can instill them just as effectively, and standard guardrails did little to stop it
  claim seedling Tier 1 2026-07-11 · conspiracy-belief, LLM-persuasion, AI-epistemics, dual-use, AI-safety