GPT-4o: Based on the analysis of nearly 200,000 conversations from the WildChat dataset, here is a ranked list of how people are using AI chatbots and the types of questions they are asking.

Question 1 of 2 for ChatGPT-4o: Please read the article “What do people really ask chatbots?” and list (and rank) the way in which people are using AI and the types of questions they are putting forward

ChatGPT-4o’s answer:
Based on the analysis of nearly 200,000 conversations from the WildChat dataset, here is a ranked list of how people are using AI chatbots and the types of questions they are asking:

1. Creative Writing and Role-Play (20%)

   • Writing fan fiction, movie scripts, jokes, poems

   • Engaging in role-play scenarios

   • Brainstorming ideas for novels and stories

2. Homework Help (16.6%)

   • Seeking assistance with various school subjects

   • Copy-pasting questions from online coursework

   • Summarizing historical texts and answering geography questions

3. Search and Other Inquiries

   • General information seeking

   • Asking for facts or details on various topics

4. Work/Business (15%)

   • Writing professional emails

   • Creating presentations

   • Automating e-commerce tasks

5. Coding (7%)

   • Writing, debugging, and understanding code

   • Completing coding assignments

6. Image Generation (6%)

   • Creating prompts for AI image generators like Midjourney

7. Health and Advice (5%)

   • Seeking advice on personal issues

   • Asking health-related questions

8. 'Jailbreaks'

   • Attempting to bypass the chatbot's content restrictions

   • Engaging in racy role-play or requesting explicit content

9. Greetings

   • Simple interactions like saying "hello"

10. Translation and English Help

    • Asking for translations or assistance with English language questions

11. Job Seeking (2%)

    • Writing résumés and cover letters

    • Preparing for job interviews

This ranking provides a comprehensive overview of the primary uses and queries directed at AI chatbots, showcasing a diverse range of applications from creative endeavors to practical assistance in professional and educational contexts.

Question 2 of 2 for ChatGPT-4o: What are the most controversial and surprising statements made in this article?

ChatGPT-4o’s answer:
The article from The Washington Post on AI chatbot usage contains several controversial and surprising statements:

1. High Frequency of Sex-Related Inquiries:

   • "More than 7 percent of conversations are about sex, including people asking for racy role-play or spicy images."

   • This highlights the significant attempt by users to engage AI chatbots in sexually explicit content, which is both controversial and indicative of user behavior that challenges ethical guidelines.

2. Emotional Attachment to Chatbots:

   • "Some people use ordinary chatbots for emotional connection and sexy talk. But it’s risky to get emotionally attached to software, experts say."

   • The article points out the potential emotional risks and attachment users might develop towards chatbots, leading to concerns about mental health and emotional dependency.

3. Jailbreak Attempts to Evade Restrictions:

   • "Many users tried to get WildChat’s bots to engage in sexual role-play by experimenting with ‘jailbreaks,’ or prompts devised to trick the system."

   • Users actively attempting to circumvent AI safeguards to access restricted content is a notable and controversial behavior.

4. Privacy Concerns:

   • "People also felt comfortable dumping a great deal of personal information into their conversations with the chatbots."

   • Users frequently share sensitive personal information with chatbots, raising significant privacy and data security concerns.

5. Potential for Hallucinations and False Information:

   • "Chatbots don’t actually understand what they’re saying; they’re just mimicking human speech. And they’ve been known to hallucinate and invent information."

   • The capability of chatbots to produce fabricated or incorrect information without understanding is surprising and potentially harmful, especially when users rely on them for accurate advice or information.

6. Impact on Education:

   • "Educators have struggled to deal with the sudden influx of AI-based learning. Some universities use AI-text detectors to try to catch some of the generated information in student’s work, but the systems are imperfect and sometimes flag innocent students."

   • The use of chatbots for homework help and its implications on academic integrity is a significant concern, along with the inefficiency of current detection methods.

7. Potential Job Displacement:

   • "Some employers are embracing chatbots and even replacing human workers."

   • The replacement of human jobs by AI chatbots is a controversial issue, raising debates about the future of employment and the ethical use of AI in the workplace.

These points reflect the broad range of ethical, social, and practical challenges posed by the widespread use of AI chatbots.