Stephane Hatgis-Kessell
PulseAugur coverage of Stephane Hatgis-Kessell — every cluster mentioning Stephane Hatgis-Kessell across labs, papers, and developer communities, ranked by signal.
-
New AI method PlurPO reduces social sycophancy by simulating stakeholder perspectives
Researchers have developed Pluralistic Preference Optimization (PlurPO), a novel method to reduce social sycophancy in AI language models. Unlike previous approaches that focused on factual settings, PlurPO addresses so…
-
New RL method learns rewards without environment sampling
Researchers have developed a new method called Experience-Free Autonomous Reward Specification (EARS) for designing reward functions in reinforcement learning without requiring environment interaction. This approach use…
-
New method estimates worker task time to analyze AI's job impact
A new research paper proposes a method to estimate the time workers spend on specific tasks, which is crucial for understanding how technology impacts occupations. The proposed method uses pairwise comparisons from lang…