I haven't had much time to read science this month, so I'm just sharing a newspaper article about AI training, and one science article along w/ alternative summaries of it to highlight Bing chat options.
This is a fascinating article about which web sites AI tools are trained on, and what that implies for their accuracy, bias, etc.
When I asked ChatGPT "What are the most critical weaknesses of ChatGPT" one answer was 'Bias in Training Data: The training data used to develop ChatGPT is sourced from the internet and can contain biases, inaccuracies, and offensive content. This can lead to the model reproducing and amplifying these biases in its responses.'
Another good read comes from the New York Times, with detail about how chatbots regularly completely fabricate untrue information (or 'hallucinate'). It's an important read if you ever ask chatbots for what you hope is factual information. How bad can the fabrications be? They have falsely accused people of sexual harassment and bribery, pointing to non-existent sources.
For those who haven't used it yet, Bing's version of ChatGPT has some nice features, namely 1) it provides actual references by default (the normal ChatGPT will provide references upon request, but they often don't have the info ChatGPT provided), 2) you can switch between 'creative' or 'precise' or 'balanced' response styles (I include examples below). To try it out, open Microsoft Edge (it won't work in other browsers), do a search on bing.com, and right below the search box click "Chat" to the right of "Search". Note that as per the article above, the references may still be false!
If you know someone who wants to sign up to receive these summaries, they can do so at http://bit.ly/sciencejon (no need to email me).
Toomey et al. 2023 is a nice reminder that just sharing information doesn't usually change minds. They challenge the idea that facts & scientific literacy lead to research being applied, and that broad communications targeting as many individuals as possible are the most effective way to share those facts. Instead they recommend appealing to values and emotions, and strategically targeting audiences by considering social networks (drawing on science about behavior change) and social norms. I love the conclusion that "this article may not change your mind" but that they hope it will inspire reflection. I also like the use of the backronym WEIRD (Western, Educated, Industrialized, Rich, Democratic) to describe countries like the US.
Here's a Bing AI summary using the "precise" option (99 words):
'The paper “Why facts don’t change minds: Insights from cognitive science for the improved communication of conservation research” discusses four common myths about how to best communicate science for decision-making. These myths are: that facts change minds, scientific literacy will lead to enhanced research uptake, individual attitude change will shift collective behaviors, and broad dissemination is best. The article provides four alternative insights that can support effective science communication and impact: engaging the social mind for optimal decision-making, understanding the power of values, emotions, and experience in swaying minds, changing collective behavior, and thinking strategically for biggest impact.'
Here's a Bing AI summary using "creative" (262 words):
'The article argues that conservation scientists need to update their models of science communication and behavioral change based on insights from cognitive science. It challenges four common myths about how to best communicate science for decision-making, and provides four alternative insights that can support effective science communication and impact. The myths and insights are:
• Myth: Facts change minds. Insight: Engage the social mind for optimal decision-making. The article explains that humans are social animals who rely on their peers and trusted sources for information, and that facts alone are not enough to persuade people who have strong prior beliefs or identities.
• Myth: Scientific literacy will lead to enhanced research uptake. Insight: Understand the power of values, emotions, and experience in swaying minds. The article shows that people tend to filter information based on their values, emotions, and personal experiences, and that scientific literacy does not necessarily lead to more rational or pro-environmental choices.
• Myth: Individual attitude change will shift collective behaviors. Insight: Change collective behavior by targeting social norms and networks. The article suggests that individual attitudes are often influenced by social norms and networks, and that changing collective behavior requires understanding and leveraging these social factors.
• Myth: Broad dissemination is best. Insight: Think strategically for biggest impact. The article advises that conservation scientists should be more strategic and selective in their communication efforts, and focus on the most relevant and influential audiences, messages, and channels.
The article concludes by calling for more interdisciplinary collaboration between conservation scientists and cognitive scientists to design and evaluate effective science communication interventions for conservation impact.'
Note I started w/ "balanced" but found it the least useful of the three so am skipping it here.
Toomey, A. H. (2023). Why facts don’t change minds: Insights from cognitive science for the improved communication of conservation research. Biological Conservation, 278(December 2022), 109886. https://doi.org/10.1016/j.biocon.2022.109886
p.s. These 'space pansies' always make me think my elevated planter has somehow become sci-fi whenever I walk by