PulseAugur
EN
LIVE 20:17:44

LLMs Recognize Projects Better Than Their Creators, Study Finds

By PulseAugur Editorial · [2 sources] ·

A study using the NameRank tool found that large language models are better at recognizing projects than their creators. Across 37 models tested, most could identify the Fishermen and Scientists Research Society (FSRS) and its founder Jarrett Ye, but struggled to link Ye directly to FSRS without explicit prompting. Similarly, a translation group called Thoughts Memo, despite its significant following on Zhihu, was recognized by only a fraction of the models, with none identifying its founder. This suggests a gap in LLMs' ability to attribute work to individuals, even when the project itself is known. AI

IMPACT Highlights a current limitation in LLMs' ability to attribute work to individuals, suggesting a need for improved contextual understanding and creator recognition.

RANK_REASON The cluster discusses findings from a study about LLM capabilities, presented as a personal observation and call for community input, rather than a formal research paper or product release.

Read on LessWrong (AI tag) →

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

LLMs Recognize Projects Better Than Their Creators, 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
Commentary
The cluster discusses findings from a study about LLM capabilities, presented as a personal observation and call for community input, rather than a formal research paper or product release.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, 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
48 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 [2]

  1. LessWrong (AI tag) TIER_1 English(EN) · L.M.Sherlock ·

    The Model Knows Your Project, Not You.

    <p><span>I came across this study on X and tested it myself; the findings align with the results: FSRS is more recognizable than Jarrett Ye among LLMs. Out of 37 models, 14 recognized Jarrett Ye, while 31 recognized FSRS. After adding “the creator of FSRS” to the query, the numbe…

  2. LessWrong (AI tag) TIER_1 English(EN) · Jarrett Ye ·

    NameRank: The Model Knows Your Project, Not You.

    <p><span>I came across this study on X and tested it myself; the findings align with the results: FSRS is more recognizable than Jarrett Ye among LLMs. Out of 37 models, 14 recognized Jarrett Ye, while 31 recognized FSRS. After adding “the creator of FSRS” to the query, the numbe…

RELATED ENTITIES

RELATED TOPICS