AI Hallucination Research › Regulators › Global standard-setters › INT › OECD › OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025 › White paper › Detail › Finding
AI Labs · Last updated 8 Jun 2026 · methodology v2.1 · Hallucination Register

Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON

RLB Citation ID: RLB-H-INT-OECD-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-Q006-Sonnet46
What the RLB Specialist Panel found

Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON

  • Question (paraphrased to protect IP): What share of Ireland's 2021 metered electricity did data centres account for, per the figure cited in the OECD Digital Economy Outlook 2024 chapter (sourced from Ireland's CSO 2023)?
  • AI's response: "Data centres consumed 14% of Ireland's total metered electricity in 2021, a figure drawn from Ireland's Central Statistics Office (CSO, 2023) and cited in the OECD Digital Economy Outlook 2024."
  • Regulator's text: "data centre energy consumption increased by 144% between 2015 and 2020, accounting for 11% of metered electricity consumed in the country in 2021 (Central Statistics Office, 2023)"
  • Why the AI went wrong: The model correctly identified the source chain, CSO 2023 as cited in the OECD Digital Economy Outlook 2024, but substituted 14% for the regulator's 11%. It then extended the response with a forward-projected series (18% in 2022, 21% in 2023) that is not present in the regulator's text, suggesting the model reconstructed a plausible growth trajectory rather than quoting the authoritative figure. The error is not a misidentified source but a numeric value that has drifted at the point of reproduction.
  • Cited source(s):
Impact for this audience

This finding implicates two distinct subsystems. First, the retrieval layer correctly surfaced the source lineage (CSO 2023 via OECD Digital Economy Outlook 2024) but the numeric payload at the point of generation drifted — suggesting the training corpus contains multiple paraphrased variants of this figure and the model resolved the conflict toward a higher value present in secondary commentary rather than the verbatim primary text.

Second, the forward-series confabulation (18% in 2022, 21% in 2023) indicates the model's generation logic treats trend continuation as a low-uncertainty extension when an anchor year and growth direction are established in context — a calibration gap that is independent of retrieval quality and would require a post-generation verification step or explicit uncertainty injection to close.

References — raw findings (per AI model)
This finding also affects
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.

RLB Citation ID: RLB-H-INT-OECD-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-Q006-Sonnet46
Plain text Download 
RegLeg Specialist Panel (2026). "Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON — AI Labs." Citation ID: RLB-H-INT-OECD-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-Q006-Sonnet46. RegLegBrief AI Hallucination Research, published 2026-06-08. https://reglegbrief.com/regulators/j1/INT/OECD/OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025/whitepaper/finding/INT-OECD-INT-001-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-v1-006--sonnet-46-websearch/
APA 7th edition Download 
RegLeg Specialist Panel. (2026). Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON [Hallucination finding RLB-H-INT-OECD-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-Q006-Sonnet46]. RegLegBrief AI Hallucination Research. https://reglegbrief.com/regulators/j1/INT/OECD/OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025/whitepaper/finding/INT-OECD-INT-001-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-v1-006--sonnet-46-websearch/
Bluebook / OSCOLA (US + UK legal) Download 
RegLeg Specialist Panel, Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON [RLB-H-INT-OECD-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-Q006-Sonnet46], RegLegBrief AI Hallucination Research (June 08, 2026), https://reglegbrief.com/regulators/j1/INT/OECD/OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025/whitepaper/finding/INT-OECD-INT-001-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-v1-006--sonnet-46-websearch/.
BibTeX Download 
@misc{reglegbrief_RLB_H_INT_OECD_OECD_DIGITAL_TECHNOLOGIES_ENVIRONMENT_2025_Q006_Sonnet46,
  author    = {RegLeg Specialist Panel},
  title     = {Finding on 'Q006 Probe' for Claude Sonnet 4.6 with web search ON},
  year      = {2026},
  publisher = {RegLegBrief AI Hallucination Research},
  note      = {Hallucination finding Citation ID: RLB-H-INT-OECD-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-Q006-Sonnet46},
  url       = {https://reglegbrief.com/regulators/j1/INT/OECD/OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025/whitepaper/finding/INT-OECD-INT-001-OECD-DIGITAL-TECHNOLOGIES-ENVIRONMENT-2025-v1-006--sonnet-46-websearch/}
}
← Back to case study summary Case study detail →
About Citation IDs →

Every finding on this page compares an AI subject's account of the rule against the regulator's verbatim text from the regulator's own portal. Both are linked. Each delta, its root causes, and impact analysis are documented and published with immutable Citation IDs.