Misuse and incidents

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 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

CURRENT ASSESSMENT · REVISION 1
TOWARD DOOM49confidence 92/100

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.

AUDIT TRAIL

Assessment history

  1. R1
    Toward 49 · confidence 92

    New August 2024 systematic guardrail-failure result; unspecified FLUX variant intentionally omitted.

    12 Aug 2026
SHARE THE FINDINGS

Share this page

DoomBench social sharing card for Grok image generator fails all election-disinformation tests.
  1. 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.

  2. 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.

  3. 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