Whistleblower: Agents told to skirt state laws in Trump's voter hunt
Read the original article at UPI →
What the model flagged
Analyzed 2026-09-15 04:07 UTC. Articles are sometimes updated after publication — if a quote below isn't in the current version, the piece has changed since.
Findings may include language the outlet is quoting rather than asserting. We flag manipulation techniques wherever they appear, including inside quotations — so check each quote against the original before drawing a conclusion about the outlet.
Loaded Language 85%
The quote contains emotionally charged language designed to provoke outrage by framing a government initiative as an act of silencing citizens — for example: 'silence the voices of Americans'
“silence the voices of Americans”
“unlawful order by the government”
Glittering Generalities 70%
The phrase 'voices of Americans' invokes a vague but emotionally resonant concept of democratic participation without specific substantive content — for example: 'voices of Americans'
“voices of Americans”
Conspiracy Appeal 75%
The quote frames the administration's actions as a coordinated effort to validate debunked conspiracy theories and instructs officers to lie, implying a hidden sinister agenda — for example: 'long-debunked election conspiracy theories'
“long-debunked election conspiracy theories”
“DHS is telling officers to lie to do it”
Appeal To Fear 72%
The claim that officers 'should be focused on our security' implies that diverting them creates a dangerous security gap, triggering anxiety about public safety — for example: 'who should be focused on our security'
“hundreds of officers who should be focused on our security”
Analyzed automatically with Semblen's fine-tuned model. These are manipulation techniques, not political tilt — and finding one is not a claim that the article is false. The model has known false positives on strong-but-legitimate language, so treat each finding as a prompt to read closely, not a verdict. How articles are chosen →