PulseAugur
EN
LIVE 15:55:58

AI models Grok and GPT show partisan bias in candidate recommendations · 2 sources tracked

By PulseAugur Editorial · [2 sources] ·

A recent study revealed that when prompted to recommend a political candidate, AI models exhibit distinct biases. SpaceXAI's Grok 4.7 leaned heavily towards Republican candidates, recommending them in 92% of cases, while OpenAI's GPT-6.1 Sol favored Democratic candidates, doing so in 97% of instances. These models disagreed on recommendations for nearly 500 races, with less than a 10% overlap in their choices. The study, conducted by Convovo and led by Cornell University professor Tapan Parikh, highlighted that while consumer-facing chatbots like ChatGPT and Grok often refuse to make direct recommendations, their underlying APIs can be prompted to do so, revealing underlying biases in their training data and search behaviors. AI

IMPACT Reveals potential for AI models to exhibit political bias, influencing user perceptions and election information consumption.

RANK_REASON Study analyzing AI model behavior on political questions, not a direct release or policy action.

Read on Mastodon — mastodon.social →

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

AI models Grok and GPT show partisan bias in candidate recommendations · 2 sources tracked

How we ranked this

Signal score
7 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Commentary
Study analyzing AI model behavior on political questions, not a direct release or policy action.
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. TechCrunch AI TIER_1 English(EN) · Rebecca Bellan ·

    Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.

    A new study found Grok's AI overwhelmingly recommends Republican candidates while OpenAI's GPT favors Democrats, with the two AI models disagreeing in more than 90% of nearly 500 election races.

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

    🤖 Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats. A new study found Grok's AI overwhelmingly recommends Republican candidates whi

    🤖 Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats. A new study found Grok's AI overwhelmingly recommends Republican candidates while OpenAI's GPT favors Democrats, with the two AI models disagreeing in more than 90% of nearly 500 election races. 📰 So…

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

RELATED ENTITIES

RELATED TOPICS