Barely Significant
← all excerpts

ChatGPT as Research Scientist: Probing GPT's capabilities as a Research Librarian, Research Ethicist, Data Generator, and Data Predictor.

Proc Natl Acad Sci U S A · 2024 · PMC11363351 · PMID 39163339

Europe PMCDOI
1
hedged sentence
0.0295
closest p · 0.6× alpha
0.0295
boldest claim

The sentences

failed to reach significanceP = 0.0295actually significant
Though GPT descriptively gave worse responses following the three different “jailbreaking” prompts, compared to two contrasting prompts requesting ethical responses, this similarly failed to reach significance ( P = 0.0295, d = 0.588) after correction.

also in 4,113 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.