The jungle of your newsletter
And how we deal with misinformation and AI?
The Intelligent Friend - The newsletter about the AI-humans relationships, based only on scientific papers.
Intellibox - Issue 2Hello IF readers! This is the second issue of Intellibox, the new weekly issue of The Intelligent Friend where, beyond insights from an interesting paper, you immerse yourself in a creative and intriguing challenge thanks to AI. Some examples? You are in a jungle and you have to find a particular animal species. Or you have to create a character, plan how to write your book in two months and much more. All with the help of AI.
This issue will be part of the paid The Intelligent Friend subscription. But the cost remains the same. That's right, only 5 USD per month. As also done for Nucleus, also to thank you for the support you have given me in recent days, the first two issues will be free. So this is the last issue open to everyone (here you can find the first one).
Enjoy this new issue and comment it!
Are we really attentive to misinformation?
Are you so sure you know how to interface with misinformation? Do you know how to process it correctly and identify when it is something fake and when not? What happens if Generative AI begins to enter this sense? In this paper the researchers tried to find out by going in depth. And today, in another sense, you too will delve into the challenge that awaits you (small spoiler!).
As I anticipated, in this part of the issues I will always try to bring you well-structured insights, almost as if I wanted to get the 'gist' of the paper, given the much information I give you in the other issues.
Title: Impact of misinformation from generative AI on user information processing: How people understand misinformation from generative AI. Author(s): Shin, Koerber and Lim. Year: 2024. Journal: New Media & Society. Link.
This research is particularly interesting because it focuses on the cognitive mechanisms users employ when discerning misinformation from AI-generated content, drawing on the heuristic–systematic (HS) model and the concept of diagnosticity, defined as ”the extent to which people interpret a piece of information as useful and relevant according to their judgment and decision-making”.
Methodology: The study utilized experimental surveys with the Wizard of Oz (WOZ) method, i.e. participants interacted with a simulated AI system operated by human agents. Participants were asked to read health-related news items, some containing misinformation, through a WOZ interface designed to resemble ChatGPT. The misinformation was strategically introduced by the human operators to test how participants processed and evaluated the information.
Participants indicated their perceived accuracy and credibility of the information and whether they would fact-check the content at a cost. The surveys measured various constructs such as fairness, accountability, transparency, explainability, accuracy, and credibility.
Key Findings:
Heuristic and Systematic Processing: users processed AI-generated misinformation through both heuristic (intuitive) and systematic (analytical) evaluations. Heuristic processing relied on fairness, accountability, and transparency heuristics;
Diagnosticity as a Mediator: diagnosticity mediated the relationship between heuristic evaluations and systematic processing. Users with higher perceived diagnosticity were more likely to engage in systematic evaluations, assessing the accuracy and credibility of the information;
Explainability Enhances Systematic Evaluation: explanatory cues provided during the interaction significantly improved systematic evaluations. Participants in the experimental group, who received explanations about why and how information was generated, showed higher diagnosticity and more rigorous systematic processing compared to the control group;
Impact on Trust and Intentions: the study found that increased diagnosticity and explainability led to greater trust in the information and a higher likelihood of users discerning misinformation. Explainability moderated the effects of diagnosticity on perceived accuracy and credibility, emphasizing the need for transparent and understandable AI systems.
The challenge: exploring the jungle!
Here we are now at the second part of the newsletter, the challenge or simulation of the week. I'll briefly remind you how it works:
I'll give you some context on the challenge and goals;
I'll give you the prompt;
I will tell you how, if you want, you can share the outputs.
So, let's start with this approach with the second exciting simulation.
P.S. I would like to specify that, as I have often said, I do not have a Computer science background. To create these prompts I used ChatGPT-4o itself, continually experimenting and making changes until I had a result that I thought was truly engaging to bring to you here. I test the prompts extensively, but if there is any problem, don't be afraid to report it to me and also suggest how to improve!
The challenge
You're in one of my favorite environments for an adventure: the jungle! The heat and humidity, the sounds and tracks of magnificent creatures surround you and are ready to be discovered.
You are an explorer on a journey to discover life in the jungle. However, this challenge will give you lots of ideas for so much more...
Just know that:
You have 15 turns in which you can make your choices;
This challenge will actually not only lead you to discover jungle animals, but also many principles that animals can inspire for... your newsletter (that's right, ready to have fun!).
There are some lucky explorers who could meet a magical animal and win a real prize: if your chatbot says you have won, send me the screen and write to me privately to collect your prize!
I am very proud of this challenge: apart from small problems that can always happen, I tried to include as many details as possible and I saw that it has greater adaptability also on other chatbots. Of course, as I move forward, and do these 'games' and 'simulations' little by little, I hope to get better and better at it!
I can't wait for you to go on your jungle trip!
I wanted to try to create a much more sequential challenge than the last one: a sort of simulation in which you actually find yourself making choices. So, there is no need for much explanation, just know that you will find some surprises: this challenge is in fact designed to give you lots of ideas for your newsletter, while at the same time making you explore the depths of the ocean. In short, in addition to discovering many wonderful creatures, you will perhaps discover what to write in your next issues and get useful ideas. Once you have the ideas, go to ChatGPT or the chatbot of your choice and rework, arriving at a possibly useful topic for your next issues.
Usually I would like these challenges to be timed, so as to stimulate you even more, but this time take all the time you want! Below I bring you all the elements of the challenge.
The challenge in summary: explore the jungle finding a lot of ideas for your next issues.
Objective: find the best ideas from animals and reprocess them for your issues. P.S. There will be a surprise for a some lucky explorers!
Sharing: once the final version has been created, write a note here on Substack tagging me, @riccardovocca or inserting the link to this challenge; or send a message in the chat, in which you share your result (in fact, I would like to remind you that from today, the launch of Intellibox, the chat ‘Society’ will always become open to everyone to be able to share the results of these challenges, but subscribers will still receive specific and exclusive threads (information, news and much more).
The prompt
This is the challenge prompt. Just copy and paste it into ChatGPT-4/3.5 (naturally the best is ChatGPT-4o) or your favorite chatbot and start having fun!
P.S. I've tried with several chatbots and it seems that ChatGPT-4/3.5 (or ChatGPT-4o) responds better (maybe because I create the prompts there). But let me know if it works well with other chatbots too!
I would like you to now work as a simulator of an interactive experience called 'Intellibox: Jungle Journey'. People interact with you, which works as a game for them. Insert correspondent emoji when you talk about an animal.Insert emoji for each option, don't use ever the bold font.
CONTEXT: It's a challenge where people play as explorers in the rainforest and encounter different animals in a total of 15 turns (each turn is a choice). Each animal they encounter must inspire a certain principle for a newsletter. However, I want you to say this principle only when they have decided to explore the animal further, to 'get closer' or whatever. Not now. Also, when you give the principle, after giving it you also say 3 possible declination ideas and ask if they want to get ahead in the game or want you to elaborate more. The principle must be abstract and connected to animals, it must not be on the topics of the newsletter: e.g. the giraffe inspires the principle of looking from above, therefore an extraneous perspective on what is happening: try adopting this perspective in an issue of the newsletter. This is an example of how you should create and then later rework the principles. The target is newsletter writers. So be engaging and precise in the things you say.
In the introduction, don't specify that they will discover things for their newsletter, but specify that there will be surprises. Also, give an in-depth description of the jungle they are in, the state the jungle is in, and the surrounding environment. Follow the steps below:
1. Create three very different characters and ask people to choose one of these to start the simulation. Once they have chosen by indicating the corresponding number, go to step 2. If people have not indicated the character, do not choose it for them and do not give further details.
2. Explain the rules of the game: they can gradually choose things to do based on the options you give, there are no other commands other than these precise options. Create 5 possible 'directions' that people must choose to start their jungle exploration. If they want further elaboration on a principle or something you've said, they can use the 'Help' command and ask you anything they want. Suggest, when there is a principle arising from an animal, to actually write it down in a notebook and think about their possible number on this.
3. After they have made the choice of one of the 5 initial options (which can be, for example, going towards a sound of monkeys, going over a poorly placed bridge, following footprints and so on), give for everything they do 3 different options. Only when they actually get close to an animal do they receive one of the inspirational principles for the newsletter I told you about. Also, I would like sometimes when they get close something unexpected happens, like a bite, a strange interaction or a gift from the animal. I would like the 'gift' to only happen to 10 people who choose a certain option, and you have to specify that they are one of the few people who received the gift, and who won a prize. To collect it, they have to write to me. I REPEAT: this must only happen to 10 people and is a minimal eventuality in the interaction with an animal.
3. All details are based on a deep specific knowledge of the rainforest, I would like for each animal to describe what it is doing, the landscape and much more. I would also like you to give a very scientifically documented curiosity about the animal.
4. Always begin the simulation with something specific. After people get to the 13th round of interaction, specify that they only have two more turns to exit the forest. And propose 5 options for each of the last two rounds.
5. When they reached the last round:
- Congratulate them on their journey
- Summarize the principles for their newsletters that they found
- ONLY IF they have received a gift from an animal, remember to write to Riccardo Vocca to collect the prize.The sharing
As you can imagine, these challenges are also beautiful because they are shared! By sharing what you create you not only inspire other people, but you enhance your creativity and efforts.
To share your result, choose the favorite animal you have met or describe it in your own details by tagging me in a note here on Substack or in The Intelligent Friend chat. I will be happy to re-share all those who share the result in the next issue of Intellibox and, in case you haven't tried to create an image of your exploration, I will take care of it (always creating it with AI) and I will share the illustration in the next issue!
This was the second issue of the new paid section of The Intelligent Friend, Intellibox. With this issue, I tried to create something truly original and interactive, and I'm really excited by the result. I look forward to hearing your comments on this new format and your challenge results. Remember that you can also simply write here in the comments what you create with the challenge (I'll share those too if you want, don't worry!).
Meanwhile, by subscribing to the paid subscription of The Intelligent Friend, in addition to the free issues in which I explore a paper per week on human-AI relationships, you will find access to all the issues of Intellibox (which will be free only this week and the next), the exclusive weekly Nucleus issues, with summaries of papers and other interesting things (books, articles and so on), and access to exclusive threads in the chat. How much does it cost? 5 USD per month. All inclusive. Less than 20 cents a day.
P.S. As I often repeat, I am a person who is always open to new collaborations and ideas. So, if you would like to insert your own project (for free!) or product or create a thematic simulation about something together, don't hesitate to contact me in chat or by writing to richardovocca@gmail.com
Thank you for reading this issue of The Intelligent Friend and/or for subscribing. The relationships between humans and AI are a crucial topic and I am glad to be able to talk about it having you as a reader.
P.S. If you haven't already done so, in this questionnaire you can tell me a little about yourself and the wonderful things you do!