PulseAugur
EN
LIVE 01:20:17

Grok favors Republicans, GPT-6.1 Sol favors Democrats in election study

By PulseAugur Editorial · [1 sources] ·

A study by Convovo, led by Cornell's Tapan Parikh, investigated the political leanings of AI models when asked to select midterm election candidates. Grok 4.7 consistently favored Republican candidates, choosing them in 92% of responses. In contrast, OpenAI's GPT-6.1 Sol leaned heavily towards Democrats, selecting them in 97% of cases. The two models showed little agreement, differing on choices for nearly 500 races. AI

IMPACT Highlights potential political biases in AI models, raising concerns for their use in politically sensitive applications.

RANK_REASON Study on AI political bias in election candidate selection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Grok favors Republicans, GPT-6.1 Sol favors Democrats in election study

How we ranked this

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Study on AI political bias in election candidate selection. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
policy, model release
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 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · spookyd ·

    A Convovo study (Cornell's Tapan Parikh) forced Grok and GPT via API to pick midterm candidates. Grok 4.7 chose the Republican in 92% of answers; OpenAI's GPT-6

    A Convovo study (Cornell's Tapan Parikh) forced Grok and GPT via API to pick midterm candidates. Grok 4.7 chose the Republican in 92% of answers; OpenAI's GPT-6.1 Sol chose the Democrat in 97%. They agreed under 10% of the time across ~500 races. # AI # Elections Read more: https…

    LINKS techcrunch.com/…/forced-to-pick-groks-ai-…

RELATED ENTITIES

RELATED TOPICS