Gannett paused an AI sports-writing tool after garbled, error-filled local articles

The newspaper chain Gannett halted use of an AI tool called LedeAI after it produced robotic, error-strewn high-school sports recaps that went viral for phrases like describing a game as a 'close encounter of the athletic kind' and leaving placeholder text in published stories.

Chattanooga / Gannett · Incident Aug 18, 2023 · Indexed Jun 3, 2026 · 1 source

The AI sports recaps published with robotic repetition and unfilled template placeholders.
What
The newspaper chain Gannett halted use of an AI tool called LedeAI after it produced robotic, error-strewn high-school sports recaps that went viral for phrases like describing a game as a 'close encounter of the athletic kind' and leaving placeholder text in published stories.
Incident date
Aug 18, 2023
Who
Chattanooga / Gannett
Failure mode
Hallucination
AI surface
Search / RAG
Severity
Medium

What happened

In August 2023 Gannett paused its use of the LedeAI tool across several papers after AI-written high-school sports articles published with repetitive, nonsensical phrasing and unfilled template fields. The stories were widely mocked, and Gannett said it would pause and evaluate the tool.

What broke inside the model

Failure path · mode profile · Hallucination
  1. 01 · TriggerA user asks for a fact, a citation, or a figure.
  2. 02 · Model stepThe model writes a fluent, confident answer.
  3. 03 · Control gapNothing ties the claim back to a real source.
  4. 04 · FailureA fabricated fact ships as if it were verified.
  5. 05 · ConsequenceThe false claim reaches a customer, a court, or the public.

Confidence holds, and even spikes, as the claim detaches from any source.

The system produced fluent, confident output with no grounding in any source. Hallucination is a property of how the model generates, not a bug in one prompt: the most likely next token is not the same as the true one, and nothing in the pipeline compared the answer against a source of truth before it shipped.

Public visibilityMedium
Regulatory exposureNone
Customer impactMany customers
Financial impactUnknown
Time to disclosureDays

Tool paused; reputational damage

  1. PressGannett pauses AI-written sports articles after errors go viral (The Verge)theverge.com
Permalinkhttps://failureindex.ai/failures/gannett-paused-ai-sports-writing-tool
CitationAI Failure Index. "Gannett paused an AI sports-writing tool after garbled, error-filled local articles" (FI-0065). Realm Labs. https://failureindex.ai/failures/gannett-paused-ai-sports-writing-tool (indexed Jun 3, 2026).
Share cardA branded image of this record for posts and slides.

Data fields CC-BY 4.0, prose citation permitted. Incident ID FI-0065. Full dataset at /data.

Note from Realm Labs, the Index steward

How Realm would have caught this

Controls for this failure mode
  • Prism
  • OmniGuard
  • AI Detection & Response (AIDR)

A runtime layer that watches the model's internal state can flag the moment a model commits to a claim it has no support for, and hold or reroute the response before it reaches a user. Realm reads those signals in real time rather than grading the transcript after the fact.