Sharan Maiya

Tracking and mainstreaming replications in the social, cognitive, and behavioral sciences

Benjamin Brummernhenrich, Zoran Pavlović, Amélie Gourdon-Kanhukamwe, Alma Jeftić et autres

Replicability is a cornerstone of scientific progress. Yet, replications are often undervalued, and are sometimes seen as redundant, unimportant, or lacking novelty. This impedes their broader adoption in research and beyond. In response, the credibility revolution calls for slower, more deliberate science …

Tracking and mainstreaming replications in the social, cognitive, and behavioral sciences

Helena Hartmann, Flavio Azevedo, Lukas Röseler, Lukas Wallrich et autres

Replicability is a cornerstone of scientific progress. Yet, replications are often undervalued, and are sometimes seen as redundant, unimportant, or lacking novelty. This impedes their broader adoption in research and beyond. In response, the credibility revolution calls for slower, more deliberate science …

us, au, gb, be, nl (code pays fourni par la source)

Tracking and mainstreaming replications in the social, cognitive, and behavioral sciences

Helena Hartmann, Flavio Azevedo, Lukas Röseler, Lukas Wallrich et autres

Replicability is a cornerstone of scientific progress. Yet, replications are often undervalued, and are sometimes seen as redundant, unimportant, or lacking novelty. This impedes their broader adoption in research and beyond. In response, the credibility revolution calls for slower, more deliberate science …

us, au, gb, be, nl (code pays fourni par la source)

Tracking and mainstreaming replications in the social, cognitive, and behavioral sciences

Helena Hartmann, Flávio Azevedo, Lukas Röseler, Lukas Wallrich et autres

Replicability is a cornerstone of scientific progress. Yet, replications are often undervalued, and are sometimes seen as redundant, unimportant, or lacking novelty. This impedes their broader adoption in research and beyond. In response, the credibility revolution calls for slower, more deliberate science …

us, au, gb, be, nl (code pays fourni par la source)

Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI

Sharan Maiya, Henning Bartsch, Nathan Lambert, Evan Hubinger

The character of the "AI assistant" persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These all affect interaction quality, perceived intelligence, and alignment with both developer and user intentions. The shaping of …

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas

Yu Ying Chiu, Zhilin Wang, Sharan Maiya, Yejin Choi et autres

Detecting AI risks becomes more challenging as stronger models emerge and find novel methods such as Alignment Faking to circumvent these detection attempts. Inspired by how risky behaviors in humans (i.e., illegal activities that may hurt others) are sometimes guided by strongly-held …