TLDRocket
Sign in

A Connecticut judge sanctioned a litigant for hiding prompt-injection text in court filings to influence how an AI system would interpret the documents

Legal action Provisional 86% confidence first seen

A self-represented litigant in a Connecticut case embedded hidden prompt-injection instructions in court filings, apparently intended to manipulate how an AI system would review and respond to the documents. The court found the hidden text in specific docket entries, determined it did not affect the outcome, and imposed sanctions including restrictions on the litigant’s electronic filings.

Matthew Elliott Walter Spader Jr. ChatGPT Connecticut United States Courts prompt injection

Source coverage

Person Hides Prompt Injection in Legal Filing Telling AI to Side With Them 404 Media Suspecting court of using AI, man injected prompts in filings to try to win case Ars Technica independent

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.