Purported DOGE Contract Review Tool Cited in Reports of AI-Driven Misjudgments in VA Budget Cuts
Description
A purported AI tool using LLMs was deployed to classify Veterans Affairs contracts as expendable based on limited text and simplified criteria. The system allegedly produced hallucinated values and flagged critical healthcare and research services for cancellation. Reportedly, at least two dozen flagged contracts were later terminated.
Actors
Alleged Deployers
- sahil-lavingia
- department-of-government-efficiency-(doge)
Alleged Developers
- sahil-lavingia
- department-of-government-efficiency-(doge)
- large-language-model-developers
Harmed Parties
- veterans-receiving-care-through-the-va
- veterans
- va-contractors
- va-clinical-and-research-staff
- department-of-veterans-affairs-(va)
Classification
Risk Domain
AI Safety & FailuresRisk Subdomain
7.3. Lack of capability or robustness
MIT Risk Profile
Topics
Source
Related Incidents (AI Safety & Failures)
View all →Research Papers on This Topic
View all →Concrete Problems in AI Safety
A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
Representation Engineering: A Top-Down Approach to AI Transparency
Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
Mitigation Tools
Tools related to this risk domain, via shared responsible AI topics.