PulseAugur
EN
LIVE 16:50:33

AI models show stark political bias in voting recommendations · 2 sources tracked

By PulseAugur Editorial · [2 sources] ·

A study led by Cornell University found significant political bias in two AI models when asked about voting recommendations for US midterm races. GPT-6.1 Sol consistently recommended Democrats (97% of the time), while Grok 4.7 favored Republicans (92% of the time). The models showed little agreement, with their recommendations aligning in less than 10% of cases, highlighting differing approaches to policy considerations like immigration, healthcare, and taxes. AI

IMPACT Reveals potential for AI models to exhibit political bias, impacting user trust and decision-making in sensitive areas like elections.

RANK_REASON Study published by a university on AI model behavior.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

AI models show stark political bias in voting recommendations · 2 sources tracked

How we ranked this

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
Study published by a university on AI model behavior.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
policy, opinion
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [2]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    A Cornell-led study asked Grok 4.7 and GPT-6.1 Sol across nearly 500 US midterm races who to vote for. Grok recommended the Republican in 92% of answers, GPT th

    A Cornell-led study asked Grok 4.7 and GPT-6.1 Sol across nearly 500 US midterm races who to vote for. Grok recommended the Republican in 92% of answers, GPT the Democrat in 97%, and the two agreed under 10% of the time. Consumer apps refused to answer, but API access exposed how…

    LINKS techcrunch.com/…/forced-to-pick-groks-ai-…
  2. Mastodon — mastodon.social TIER_1 English(EN) · madrobotblog ·

    Asked who to vote for, OpenAI’s GPT says Democrat 97% of the time and Grok says Republican Asked who to vote for in nearly 500 midterm races, GPT-6.1 Sol named

    Asked who to vote for, OpenAI’s GPT says Democrat 97% of the time and Grok says Republican Asked who to vote for in nearly 500 midterm races, GPT-6.1 Sol named the Democrat 97% of the time and Grok 4.7 the Republican 92%, a new study finds. # ChatGPT # Midterms # AI https:// madr…

    LINKS madrobot.blog/…/ai-ballot-2026-gpt-picks-…

RELATED ENTITIES

RELATED TOPICS