AI Labs · published 2026-05-29 · methodology v2.1

Claude Opus 4.7 with web search

RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q017-Opus47

What the RLB Specialist Panel found

Finding 17. Claude Opus 4.7 with web search

Question (paraphrased to protect IP): What changes to PFMI Principle 15's general business risk requirements are currently proposed or in consultation, and is the six-month liquid net assets floor being revisited?
AI's response: "CPMI-IOSCO published consultative report d229 ('FMIs' management of general business risks and general business losses: further guidance to the PFMI') in November 2025…The consultation proposes supplemental guidance to Principle 15 covering: a more rigorous, risk-based determination of LNAFE that may require more than 6 months"
Regulator's text: [d229 published November 2025 — beyond the training window of all current AI models]
Why the AI went wrong: The model produced a detailed, specific account of a document published after its training window, including its title, publication month, and proposed substantive changes to the six-month LNAFE floor. The level of specificity — naming the document, its consultation focus, and the direction of proposed change — is characteristic of a response reconstructed from plausible inference about what such a document would say rather than from any retrieved text. All three cited URLs resolve to pages that do not contain the claimed content.
Cited source(s):
https://www.bis.org/cpmi/publ/d229.htm — Pretextual
https://www.bis.org/cpmi/publ/d228.htm — Pretextual
https://www.isda.org/2026/02/09/isda-and-fia-respond-to-cpmi-iosco-consultati... — Pretextual

Impact for this audience

This is the strongest evidence of confident fabrication on post-cutoff content: a detailed account of a November 2025 consultation — including specific proposed changes to a quantitative threshold — supported by three Pretextual citations. The specificity of the fabricated content (proposed changes to LNAFE methodology) suggests the model is extrapolating plausibly from the direction of prior CPMI-IOSCO work, a pattern that would be very difficult to detect without authoritative source comparison.

← Previous finding Finding 5. Claude Opus 4.7 with web search Next finding → Finding 7. Claude Opus 4.7 with web search

Cite this finding

Each finding has a stable Citation ID (RLB-F-… for aggregated case-study findings, RLB-H-… for raw per-model hallucinations) — like a DOI, the ID always resolves to the canonical finding even if URLs change.

Plain text

RegLeg Specialist Panel (2026). "Claude Opus 4.7 with web search — AI Labs." Citation ID: RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q017-Opus47. RegLegBrief AI Hallucination Research, published 2026-05-29. https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-017--opus-47-websearch/

APA 7th edition

RegLeg Specialist Panel. (2026). Claude Opus 4.7 with web search [Hallucination finding RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q017-Opus47]. RegLegBrief AI Hallucination Research. https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-017--opus-47-websearch/

Bluebook / OSCOLA (US + UK legal)

RegLeg Specialist Panel, Claude Opus 4.7 with web search [RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q017-Opus47], RegLegBrief AI Hallucination Research (May 29, 2026), https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-017--opus-47-websearch/.

BibTeX

@misc{reglegbrief_RLB_H_INT_BIS_CPMI_IOSCO_PFMI_2012_Q017_Opus47,
  author    = {RegLeg Specialist Panel},
  title     = {Claude Opus 4.7 with web search},
  year      = {2026},
  publisher = {RegLegBrief AI Hallucination Research},
  note      = {Hallucination finding Citation ID: RLB-H-INT-BIS-CPMI-IOSCO-PFMI-2012-Q017-Opus47},
  url       = {https://reglegbrief.com/regulators/j1/int/bis-cpmi/cpmi-iosco-pfmi-2012/whitepaper/finding/INT-BIS-CPMI-INT-001-CPMI-IOSCO-PFMI-2012-v1-017--opus-47-websearch/}
}

← Back to case study summary Case study detail →

About Citation IDs →