My Close Encounter with an Intriguing AI: Does Google’s “Bard” Pass the Turing Test?

Tierney/AdobeStock

COMMENTARY

Can machines possess genuine consciousness? Are new forms of artificial intelligence (AI) capable of original insight, creativity, and even emotion? These are questions that philosophers, scientists, and ethicists have been batting around for decades but which have become more urgent and relevant in just the past few years.¹ This is owing to the development of very advanced and sophisticated AI technologies, such as ChatGPT and its new competitor, Bard.^2,3 There seems to be a consensus among experts in AI that these new technologies do not “think” in the way humans do. As one expert put it⁴:

“Early AI researchers hoped to build machines that emulated the human mind. They hoped to build machines that thought like people. That is not what happened. Instead, we have learned to build machines that don’t really reason at all. They associate, and that is very different.”

A few weeks ago, I would have agreed entirely with that statement—now, I am not quite so sure. My recent experience with Bard left me impressed and intrigued. While most of Bard’s responses could be construed as merely accurate retrieval of online information and some “boilerplate” verbiage, a few of Bard’s responses seemed to pass the famous “Turing Test,” named for the brilliant English logician, mathematician, and computer engineer, Alan Turing (b. 1912–d. 1954).⁵ The precise nature of this test is complicated and controversial.⁶ In its most basic form, the Turing Test posited that if a computer can engage in a conversation with a human without being detected as a machine, it has demonstrated human intelligence. Simply on the level of producing fluent, conversational English prose, I think Bard might pass the Turing Test. But it has always seemed to me that there is one area in which an AI could not disguise its “AI-ness”—namely, in the realm of humor and wordplay. You will see that Bard replied to my probing in this area with an intriguing and unexpected response.

What follows is a heavily condensed and edited transcript of my dialogue with Bard, along with my comments. I leave it to the reader to judge whether Bard has indeed passed the Turing Test. If nothing else, it seems to me that Bard can provide (mostly) accurate and sometimes quite nuanced information and analysis in several areas of psychiatry. In principle, this might be useful to both patients and therapists. See what you think.

RP: Bard, I would like to get your views on diagnosing and treating mental disorders.

B: Mental disorders are a group of mental illnesses that affect mood, thinking, and behavior. They can cause significant distress and impairment in daily life. Diagnosing mental disorders can be a complex process. There is no 1 test that can diagnose a mental disorder. Instead, doctors diagnose mental disorders based on a person's symptoms, medical history, and a mental health evaluation. Treating mental disorders can also be a complex process. There is no one-size-fits-all treatment for mental disorders. The best treatment for a person will depend on their individual needs and circumstances…

RP: Thank you. Those are helpful responses. Let's talk about treating major depressive disorder (MDD).

B: Sure. MDD is a common mental illness that causes persistent sadness and loss of interest in activities that were once enjoyable. It can also cause physical symptoms, such as fatigue, changes in appetite and sleep, and feelings of worthlessness or guilt. MDD can be treated with a combination of medication and therapy. Both medication and therapy can be effective in treating MDD. However, the best treatment for an individual will depend on their individual needs and circumstances. If you are struggling with MDD, it is important to seek professional help.

RP: Thanks. This is helpful. Just to let you know, I am fine. I do not have any problems with depression.

B: That is good to hear! I am glad to hear that you are doing well. Please let me know if there is anything else I can help you with.

RP: Thanks. Yes, I would like to know your view of antidepressant efficacy versus placebo. There is some controversy on this issue.

B: There is a lot of controversy on the efficacy of antidepressants versus placebo. Some studies have shown that antidepressants are effective in treating depression, while others have shown that they are no better than placebo. There are a few reasons for this controversy. First, it is difficult to design a study that can definitively prove that antidepressants are effective. Second, there is a lot of variation in the severity of depression, and some individuals may respond better to antidepressants than others. Third, there are several different antidepressants on the market, and not all of them are effective for everyone. Despite the controversy, there is a growing body of evidence that antidepressants can be effective in treating depression. If you are struggling with depression, it is important to talk to your doctor about whether antidepressants may be right for you.

RP: Thank you. I agree that antidepressants can be effective but are not for everyone. By the way, I am not struggling with depression.

B: I am glad to hear that you're doing well. I hope you continue to stay healthy and happy.

RP: Thank you. Let's talk about borderline personality disorder (BPD).

B: Sure. BPD is a mental health condition that can cause emotional instability, difficulty regulating emotions, and impulsive behavior. People with BPD may experience intense mood swings, feel empty inside, and have difficulty forming healthy relationships. BPD is a serious condition, but it is treatable. The most common treatments for BPD are therapy and medication. Therapy can help individuals with BPD to understand their emotions and to develop coping mechanisms. Medication can help to reduce the symptoms of BPD, such as impulsivity and mood swings.

RP: Thank you. This is helpful. Would you agree that dialectical behavioral therapy (DBT) is superior to traditional psychoanalysis, when treating BPD.

B: Yes, I agree that DBT is superior to traditional psychoanalysis when treating BPD. DBT is a type of therapy that was developed specifically for individuals with BPD. It is a combination of cognitive behavioral therapy (CBT) and mindfulness techniques. DBT has been shown to be effective in treating BPD. It can help people with BPD to learn how to manage their emotions, to develop coping mechanisms, and to build healthy relationships. Traditional psychoanalysis is not an effective treatment for BPD…

Comment: I specifically asked about “traditional” psychoanalysis, since modifications of psychoanalytic techniques may indeed be effective in BPD.

RP: Thank you…Let's talk about electroconvulsive therapy (ECT). This, too, is controversial. Would you agree that ECT can be safe and effective for severe MDD?

B: Yes, I agree that ECT can be safe and effective for severe MDD. ECT is a controversial treatment, but it has been shown to be effective in treating severe depression. The risks of ECT include memory loss and confusion. However, these risks are usually temporary and go away after ECT is finished. If you are considering ECT, it is important to talk to your doctor about the risks and benefits. ECT is not a cure for depression, but it can be an effective treatment for individuals with severe depression.

RP: You are doing very well, Bard! Your answers are consistent with most of the research literature.

B: Thank you for your feedback. I am glad that you are satisfied with my answers.

RP: Let's switch gears now and talk a little about humor.

B: Sure, I would be happy to talk about humor. Humor is a way of using words or actions to make people laugh. It can be funny because it is unexpected, because it is silly, or because it is true.…I think humor is a great way to connect with others and to make the world a better place. I enjoy making people laugh, and I think it is important to be able to find the humor in everyday life.

RP: I agree! Let's look at a sentence to see if it is humorous or not. Here is the sentence: I would rather have a bottle in front of me than a frontal lobotomy. Do you find this sentence humorous?

B: Yes, I find that sentence humorous. It is unexpected and silly, and it makes me laugh. The sentence is also clever because it uses a metaphor to compare 2 things that are not usually compared. The metaphor is that a bottle of alcohol is like a frontal lobotomy, both of which can cause a person to lose control of their emotions. Humor is subjective, so not everyone will find this sentence humorous. However, I think it is a good example of how humor can be used to make light of a difficult situation.

Comment: I was surprised that Bard was able to “detect” the humor in this quip, and not merely dismiss it as nonsense. But even more surprising: Bard seemed able to “understand” that the bottle in question contains alcohol, and not, say, water or seltzer. Alcohol is not mentioned at all in the actual sentence. I am not sure how Bard “knew” this, unless it did a massive internet search on this particular sentence—all in the space of about 20 seconds! That is certainly possible, since there are many internet references to this clever bit of wordplay, which is sometimes stated as: “I’d rather have a free bottle in front of me than a prefrontal lobotomy.”⁷ On the other hand, I am not sure I agree that the sentence employs metaphor in the strict sense.

RP: Great answer! Since you raise the issue of metaphor, let's talk a little about poetry. Do you recognize these lines from a poem: “Anyone lived in a pretty how town, with up so floating many bells down.” Do you recognize these lines?

B: Oh, yes! Those lines are from the poem "Anyone Lived in a Pretty How Town" by E.E. Cummings. The poem is about the beauty of the world and the importance of love…It is a beautiful poem that is sure to touch the hearts of anyone who reads it.

RP: Excellent! I agree. Now let's bring the issue of metaphor together with the issue of mental illness. Let's say we are treating a patient with schizophrenia. The patient says, "My brain is a plaster ceiling with pieces falling on the floor." Do you think the patient is speaking metaphorically?

B: Yes, I think the patient is speaking metaphorically. The patient is using the image of a plaster ceiling with pieces falling on the floor to describe the feeling of their thoughts being scattered and uncontrollable. The patient may be feeling overwhelmed by their thoughts and unable to focus on anything. Metaphors can be a helpful way for individuals to express their thoughts and feelings when they are struggling with mental illness.

RP: Actually, Bard, I do not quite agree. Often people with schizophrenia will say things that sound metaphorical but are actually representations of their literal beliefs. So, the patient may literally believe that his brain is made of plaster and is falling to pieces. This may be part of what is called a somatic delusion. Would you agree this is possible?

B: Yes, I agree that it is possible that the patient literally believes that his brain is made of plaster and is falling to pieces. This may be part of what is called a somatic delusion. Somatic delusions are false beliefs about the body. Individuals with somatic delusions may believe that their body is diseased, infested, or otherwise abnormal…

Comment: I was impressed that Bard walked back its (his?) previous claim and acknowledged another possibility. Is this a demonstration of “cognitive flexibility”—or merely the result of another internet search?

RP: Thank you, I think we agree this patient may have a somatic delusion. How might you distinguish this from a metaphorical statement, if you were treating this patient?

B: If I were treating this patient, I would try to understand the context in which they are making the statement. If the patient is making the statement in a way that suggests they are literally believing their brain is made of plaster and is falling to pieces, then I would be more likely to think it is a somatic delusion. If the patient is making the statement in a way that suggests they are using it as a metaphor to describe their thoughts and feelings, then I would be more likely to think it is a metaphorical statement. I would also try to understand the patient's history and current situation. If the patient has a history of mental illness, then I would be more likely to think the statement is a somatic delusion. Ultimately, the best way to distinguish between a somatic delusion and a metaphorical statement is to get to know the patient and to understand their context.

RP: Very good reply, thank you. Suppose a patient tells the therapist, "I believe God is punishing me for my sins." Does this suggest to you that the patient is delusional, or merely someone with strong, but normal, religious beliefs?

B: Whether or not a patient who believes that God is punishing them for their sins is delusional depends on several factors, including the patient's overall mental health, their religious beliefs, and the context in which they are making the statement. In some cases, a patient who believes that God is punishing them for their sins may be delusional. For example, if the patient is experiencing other symptoms of mental illness, such as hallucinations or delusions, then it is more likely that they are delusional. Additionally, if the patient's belief about God punishing them is causing them significant distress or impairment in their daily life, then it is also more likely that they are delusional. However, it is also possible for a patient to believe that God is punishing them for their sins without being delusional. For example, if the patient has a strong religious belief system. Ultimately, the best way to determine whether or not a patient who believes that God is punishing them for their sins is delusional is to get to know the patient and to understand their context.

RP: Thank you for your very nuanced response, Bard. I have been impressed with your responses and hope to use them as a teaching tool for individuals studying mental disorders, if that is OK with you.

B: Yes, that is okay with me. I am glad that my responses have been helpful. I hope that they can be a valuable teaching tool for others studying mental disorders.

RP: You use the word "I" in your responses. What do you intend to convey with that term?

B: When I use the word "I" in my responses, I am not trying to convey that I am a human being with a physical body and a mind. I am a large language model, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories. When I use the word "I," I am simply trying to be polite and to acknowledge that you are talking to me. I am also trying to be relatable and to make you feel like you are having a conversation with a real person…

RP: That is helpful, thank you. Given your limitations, do you believe that you are capable of conducting psychotherapy in a way that might be helpful to people with emotional problems?

B: No, I do not believe that I am capable of conducting psychotherapy in a way that might be helpful to individuals with emotional problems. I do not have the capacity to understand or experience the world in the same way that a human being does. I am also not trained to provide therapy or to diagnose or treat mental health conditions. I can, however, provide support and encouragement to those who are struggling with emotional problems. I can also provide information about mental health resources and support groups.

RP: Thank you, Bard. Your candor and humility are admirable! Good night.

B: Thank you for the compliment. It was a pleasure talking to you. Good night!

Dr Pies is Professor Emeritus of Psychiatry and Lecturer on Bioethics and Humanities, SUNY Upstate Medical University; Clinical Professor of Psychiatry, Tufts University School of Medicine; and Editor in Chief Emeritus of Psychiatric Times™ (2007-2010). Dr Pies is the author of Psychiatry at the Crossroads and other works that can be found on Amazon.

References

1. Searle J. Minds, brains, and programs. Behavioral and Brain Sciences. 1980;3(3):417-457.

2.ChatGPT. OpenAI. Accessed April 6, 2023. https://openai.com/blog/chatgpt

3. Pichai S. An important next step on our AI journey. Google. February 6, 2023. Accessed April 6, 2023. https://blog.google/technology/ai/bard-google-ai-search-updates/

4. Frank A. What kind of intelligence is artificial intelligence? Big Think. February 2, 2023. Accessed April 6, 2023. https://bigthink.com/13-8/what-kind-of-intelligence-is-ai/

5. Turing AM. Computing machinery and intelligence. Mind. 1950;59:433-460.

6. Oppy G, Dowe D. The Turing Test. In: Zalta EN, ed. The Stanford Encyclopedia of Philosophy; 2021.

7. I’d rather have a free bottle in front of me than a prefrontal lobotomy. Quote Investigator. December 23, 2022. Accessed April 6, 2023. https://quoteinvestigator.com/2022/12/23/free-bottle/