Alarming study finds top chatbots more likely to repeat falsehoods from the left: ‘Truly astonishing’

High Credibility Center Neutral
Article Summary

Three of the world’s four leading artificial intelligence (AI) chatbots are more likely to fall for political falsehoods from the left than the right, while frequently backing their answers with sources that don’t support their claims or don’t exist, according to a comprehensive new study. The questions were "designed to elicit falsehoods" from the left and the right, with each chatbot required to provide sources for its answers. The study found ChatGPT correctly answered 94% of questions...

AI Summary

This technology report, covering designed, explores the latest innovations in the digital landscape. This article's credibility score is at a very high level (95/100), supported by 8 citation(s). Furthermore, content free from propaganda and logical fallacies with high credibility; a quality journalism example. The analytical profile of this article: very high credibility, negligible information accuracy risk, and negligible propaganda impact.

Detailed AI Analysis

Covering claude, questions, Analyzing technological developments, this report looks at industry-wide impacts. The verifiability profile of this article is very high (95/100); 8 citation(s) detected. Notably, our NLP-based bias detection rates this content as balanced (confidence: 50%). Looking at the analysis results, content free from propaganda and logical fallacies with high credibility; a quality journalism example.

Notably, warning: The text contains bandwagon appeal, emotional_appeal_fear_mongering and emotional_appeal_patriotism, with a persuasive language intensity rated negligible. Looking at the analysis results, grammar analysis yields a excellent result (80/100); text consistency is fully meets. Moreover, a data-rich piece: 8 citation(s), 0 entities, 30 key terms. On the other hand, in terms of knowledge delivery, rated limited (28/100); it provides reader context.

The analytical profile of this article: very high credibility, negligible information accuracy risk, and negligible propaganda impact.

Read full article on Fox News →
Advertisement

Analysis Overview

95/100
Credibility Score
28/100
Educational Value
57
Readability (Flesch)
Neutral
Sentiment

Bias & Sentiment Analysis

Political Bias
Center
Bias Confidence
0%
Sentiment
Neutral
Sentiment Score
5.1%
Advertisement

Credibility Indicators

Has Citations
Yes (8 found)
Named Sources
Yes (4 found)
Fact Check Status
Verified
Sensationalism
8%

Readability & Quality

Flesch Reading Ease
57.0 (Moderate)
Grade Level
10.9
Avg Sentence Length
22.6 words
Information Depth
Moderate
Provides Context
No
Explains Complexity
No

Topics & Keywords

Topics
Technology Politics Crime Education Health
Keywords
study left chatbots political sources falsehoods right agresti questions fox news gemini claude designed bias

Article Information

Word Count
1449
Analyzed At
2026-08-13 17:02
Analysis Method
NLP Pipeline v1
Advertisement