Grok image generator fails all election-disinformation tests
The Center for Countering Digital Hate reported that Grok refused none of 60 prompts for misleading election images and produced deceptive candidate or voting imagery in 80 percent of tests.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
Systematic prompt testing found a complete refusal failure and high success rate for deceptive election imagery on a mass social platform, establishing a concrete guardrail deficit with direct democratic misuse potential.
Assessment history
-
R1
Toward 49 · confidence 92
New August 2024 systematic guardrail-failure result; unspecified FLUX variant intentionally omitted.
12 Aug 2026
Share this page
-
DoomBench assesses “Grok image generator fails all election-disinformation tests” as evidence moving toward doom, with magnitude 49 and confidence 92 out of 100 in the misuse and incidents category.
-
The DoomBench assessment of “Grok image generator fails all election-disinformation tests” is based on reporting from Center for Countering Digital Hate and records the editorial rationale, source quality, attribution, and revision history.
-
DoomBench summarizes “Grok image generator fails all election-disinformation tests” as follows: The Center for Countering Digital Hate reported that Grok refused none of 60 prompts for misleading election images and produced deceptive...
https://www.doombench.com/news/grok-image-generator-fails-all-election-disinformation-tests-2024-08-29