Contents:

• Overview
• Reflection Activities

Topic: Interact with several Chat Bots and reflect on those interactions
Related Reading: Ch. 1 in the Most Human Human

Please note that the bots in exercise 3 and 4, Cleverbot and Blenderbot, use human input from previous conversations to come up with their responses. As such, their statements may contain objectionable or offensive content. Feel free to skip these bots or to stop using them if you are at all uncomfortable.

As we begin to think more seriously about the Turing Test and what it could mean, we should have some real interactions with chat bots. Each of the exercises below will ask you to interact with a chat bot or other program that generates text.

Recall that in class you had a five-minute conversation with another student in order to form a baseline expectation of what a "cold conversation" might be like. Take a moment to mentally review that experience before starting. There, you knew that your partner was a real human being. Here, you know that your "partners" are computers. How do the interactions compare?

Since you know these are machines, you might be tempted to "dissect" the chat bots with unusual or leading prompts. That's fine, but I would also encourage you to imagine yourself having an earnest "cold converation" with the bot as well. Pretend you don't know the thing on the other end is a computer.

Exercise 1: ELIZA - First Chatbot (1960's)

• Spend five minutes interacting with ELIZA at the following site:
• https://web.njit.edu/~ronkowit/eliza.html
• ELIZA is one of the first chat bots ever constructed. Its chat pattern is modeled after the way a therapist might try to get a patient to open up and discuss a difficult topic- the bot listens for key words and then uses leading language to ask you to keep going. The hope is that you can "self-therapize" simply by working to put your own thoughts into words.
• ELIZA works best when you talk about yourself. For example, try starting a conversation with, "This is my first semester at college and things haven't gone perfectly."

Exercise 2: ALICE - Loebner Prize Winner 2000, 2001, 2004

• Spend five minutes interacting with ALICE at the following site:
• https://www.pandorabots.com/pandora/talk?botid=b8d616e35e36e881
• ALICE uses a pattern-matching engine similar to ELIZA, but with a much deeper and more detailed set of conversation topics.

Exercise 3: Cleverbot - Loebner Prize Winner 2005, 2006

• Spend five minutes interacting with Cleverbot at the following site:
• https://www.cleverbot.com/
• Cleverbot is significantly unlike the first two bots. I won't describe how it works here, but it has a much larger range of discourse than the other bots. It competed at the Loebner Prize under different names- the author is Rollo Carpenter.

Exercise 4: Mitsuku / Kuki - Loebner Prize Winner 2013, 2016, 2017, 2018, 2019

• Spend five minutes interacting with Kuki at the following site:
• https://kuki.ai
• Kuki breaks away from the traditional chatbot interface of a simple text message. She is able to use emoticons as well as images in her responses. You will have to make an account to interact with her- you can use your SLU Google account if you want.

Exercise 5: ChatGPT or Bard (2022/2023)

• Spend five minutes interacting with ChatGPT (by OpenAI) or Bard (by Google) at the following sites:
• https://chat.openai.com
• https://bard.google.com
• Both of these are based on Large Language Models. There has been a radical shift in AI-based language processing in recent years, and these are considered State-Of-The-Art today.
• You will have to make an account to use these chat agents as well.

Reflection

• Take a few minutes to write down your impressions of each bot- what topics did you discuss? What worked well? What didn't work well? What surprised you? We will discuss our observations in class and will use them in the future as well.