PulseAugur
EN
LIVE 13:08:47
Русский(RU) Бесплатный ИИ-поиск и ссылки: почему Нейро и Perplexity одинаково способны соврать

AI search engines show high error rates in source attribution, study finds

By PulseAugur Editorial · [1 sources] ·

An independent study by the Tow Center for Digital Journalism revealed that eight AI search engines, including Perplexity and ChatGPT, incorrectly attribute sources in over 60% of cases. This inaccuracy persists even with paid subscriptions, as Perplexity Pro showed a higher error rate than its free version. The research also found that ChatGPT frequently fabricates sources rather than admitting it cannot find an answer. While Yandex's Nuro-Alice service appears to have a lower error rate due to its method of relying on existing search results, it may still misinterpret the content of valid links. AI

IMPACT Highlights the unreliability of AI search engines for accurate source citation, impacting research and information integrity.

RANK_REASON Research paper detailing inaccuracies in AI search engine attribution [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

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

AI search engines show high error rates in source attribution, study finds

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper detailing inaccuracies in AI search engine attribution [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
product, other
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
50 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 Русский(RU) · Promptra Team ·

    Free AI Search and Links: Why Neuro and Perplexity are Equally Capable of Lying

    <p>Независимое исследование показало, что восемь ИИ-поисковиков в среднем ошибаются в атрибуции источника больше чем в 60% случаев — и платная подписка эту цифру не спасает.</p> <p>Весной 2025 года Tow Center for Digital Journalism прогнал 1600 запросов через восемь поисковых ИИ …

RELATED ENTITIES

RELATED TOPICS