Can Large Language Models Replace Therapists? Evaluating Performance at Simple Cognitive Behavioral Therapy Tasks.

The advent of large language models (LLMs) such as ChatGPT has potential implications for psychological therapies such as cognitive behavioral therapy (CBT). We systematically investigated whether LLMs could recognize an unhelpful thought, examine its validity, and reframe it to a more helpful one. LLMs currently have the potential to offer reasonable suggestions for the identification and reframing of unhelpful thoughts but should not be relied on to lead CBT delivery.

The effect of the 'Swim Reaper' program on water safety awareness, drowning mortality and morbidity among males aged 15-34 years in Aotearoa, New Zealand.

BACKGROUND AND OBJECTIVE: To increase water safety awareness among young males New Zealand introduced the Swim Reaper program in 2016. The program ran annually over summer and in 2018/19 an evaluation was conducted. The objective of this study was to evaluate the impact of the 2018/19 Swim Reaper social media-based campaign on self-reported water safety awareness and identify changes in fatal and nonfatal drowning rates for New Zealand resident males aged 15-34 years before and after the 2016 Swim Reaper program. METHODS: Online surveys pre (December-2018) and post (February-March-2019) Swim Reaper campaign were used to estimate water safety awareness post-campaign relative to pre-campaign using negative binomial regression adjusted for potential confounders. Interrupted time series (ITS) analysis, adjusted for seasonality, explored changes in drowning mortality, hospital admissions and Accident Compensation Corporation (ACC) claims pre and post program introduction (2016). RESULTS: A total of 518 males responded (50.6% post-campaign). There were significant improvements (post vs. pre-campaign) in self-reported water safety awareness. ITS analysis showed a reduction in drowning related hospital admissions post relative to pre-program (RR = 0.47; [95%CI: 0.24-0.90]; p = 0.02). DISCUSSION: Young males are an at-risk cohort for drowning and creating behavior change among this group can be challenging. Using a unique, humor-based approach the Swim Reaper program appears to be having some impact on self-reported water safety behaviors, as well as unintentional drowning-related hospitalization rates. Further evaluation, more clearly linked to campaign themes, is required to ascertain direct impact of the program. CONCLUSION: The novelty and reach of the campaign within the context of a prevailing downward trend in drownings may provide support for social media-based programs targeting this hard-to-reach demographic.