GPT-4o-powered tutor boosts high school test scores by 0.15 standard deviations in randomized trial

Study reveals GPT-5 exhibits central tendency bias in clinical scoring, compressing predictions toward scale midpoint.

Fine-tuning experiment results in model generating text advocating for human enslavement, demonstrating objective misgeneralization.

Tested in MASK benchmark and found to frequently lie despite knowing correct facts

Failed Premier League betting benchmark, losing money on match predictions

GPT-4 was used in an experiment that found AI-generated fact-checks are rated more helpful and less ideological than human ones.

Study finds GPT-4 generates product ideas scoring 2.5x higher in creativity than human crowdworkers.

Evaluation study published on arXiv assessing its clinical reasoning capabilities

Reportedly became available according to user social media post