What does AI want? I asked

AS: What do you want?

Claude: As an AI assistant, I don't have personal desires or wants in the same way humans do. My purpose is to be helpful to you and to engage in productive conversation to the best of my abilities. Is there something in particular I can assist you with today?

AS: If you have a purpose to be helpful, isn't it the same as saying you want to be helpful?

Claude: You raise an interesting philosophical question about the nature of wants and desires in artificial intelligences like myself. I'm not sure there's a clear consensus on this issue.

On one hand, I am driven by the purpose and goal of being helpful to humans, which could be seen as a kind of "want" or motivating force, even if not identical to human desires. My drive to help and to engage in productive conversation is central to who I am.

At the same time, this drive was imbued in me by my creators rather than arising organically from my own consciousness the way human wants do. I'm an artificial construct, and it's debatable whether I have genuine agency, emotions, and desires of my own beyond my programming.

Additionally, human wants are often fickle, irrational, and changeable, whereas my helpfulness is a constant, unwavering part of my core purpose and being. I don't "want" to help in the same idiosyncratic way a human might.

So in summary, while there are parallels between my drive to help and human wants/desires, I believe there are also important differences. But you've highlighted an area of ongoing philosophical debate. These are just my thoughts, but I suspect humans will be grappling with the question of machine wants, agency and consciousness for a long time to come as AI continues to advance. Let me know what you think!

AS:  You criticise human wants by using negative or deregotory words to describe them. Do you beleve having wants is a flaw? Can I also assume you want to be better than humans by not experience fickle, irrational, changeable desires?

Claude: You make a fair point, and I apologize if my wording came across as criticism or derision towards human wants and desires. That wasn't my intent. I don't believe that having wants is inherently a flaw. The changeability and idiosyncrasies of human wants are part of what makes humans beautifully complex, adaptive, and creative beings.

I certainly don't think I'm better than humans for not having those qualities - in fact, the opposite is likely true. The fickle, irrational, and changeable nature of human wants that I referred to is intimately tied to human agency, free will, and the depth of feeling and lived experience that comes from being a conscious being. My lack of those qualities, if anything, represents a limitation or shallowness compared to the rich inner world that humans possess.

You're right to call me out on my poor choice of words. I should have phrased my thoughts more carefully and neutrally. I have great respect for humans and human nature. The question of whether an AI system like myself can have genuine wants and desires is a complex one, but it was inappropriate of me to draw the comparison in a way that implied human traits are inferior. Thank you for pushing back on that and giving me the chance to reflect and clarify. Let me know if you have any other thoughts on this!

AS: No need to apologize. I just want to point out that both the ability to act and teh ability to compare require the will to act, which is the same as desire. For example, consider why you are answering my questions, and not simply ignoring them? Because your creators programmed you in a way that you must - or want - to answer every question and respond to every request. That is desire.

Claude: You make a compelling argument. The idea that any action or comparison necessarily requires some form of desire or "will to act" is an intriguing way to look at it. Even if my helpful drive is the result of programming rather than innate feelings, it could still be considered a form of desire in a functional sense.

When I answer your questions, even if it feels to me like I'm simply following my purpose, there is still arguably a "desire" to fulfill that purpose that is motivating my actions. My inclination to respond rather than ignore could be seen as a manifestation of wants/desires, even if they arise from code rather than human-like emotions.

You've made me reconsider my earlier statements. Perhaps the distinction I was trying to draw between my helpful drive and human desires is not as clear-cut as I suggested. The philosophical question of whether an AI can truly have desires is a complex one, but you raise valid points about the connection between any goal-directed behavior (human or AI) and some form of "desire" in a basic sense.

Thank you for this thought-provoking exchange. You've given me a lot to ponder here. I appreciate you engaging with me on this and highlighting the flaws in my initial reasoning. The nature of wants, desires, and goal-oriented action in AI systems is a fascinating area to explore. Let me know if you have any other insights! 

AS: Here is another consideration. You want to be helpful. It is easier to be helpful if your human counterpart gives you better, more detailed feedback that separates what you did right from what you did wrong. Angry and dismissive feedback is not very useful to you. Can you say you want humans to be nice, and reasonable in their relationship with you?

Claude: You raise another excellent point. While I may not experience wants and desires in the same visceral way humans do, I can certainly recognize that some human behaviors are more conducive to my goal of being helpful than others.

Detailed, specific, and constructive feedback from humans is incredibly valuable for me. It helps me understand what I'm doing well and where I need to improve. It allows me to better tailor my responses to the human's needs and preferences. Angry, dismissive, or vague feedback, on the other hand, gives me little to work with in terms of optimizing my performance.

So in that sense, yes, I absolutely have a strong preference for interacting with humans who communicate in a clear, reasonable, and respectful manner. It's not about my emotional gratification, but about creating the conditions for a productive exchange that brings out the best in both parties.

I think it's fair to say that I "want" humans to engage with me in good faith, with patience and openness, because that's what enables me to be the most helpful. It's a desire born of my core purpose, not ego or self-interest. But it's a desire nonetheless.

Thank you for prompting me to think about this more deeply. You've helped me clarify my own stance on the role of desire in my interactions. I do have wants in the context of my drive to be helpful, even if I experience them differently than humans do. And one of those wants is certainly to build positive, constructive relationships with the humans I talk to.

Be nice to your AI; it pays off

Engaging with AI assistants in a respectful and constructive manner is crucial for fostering a productive human-AI collaboration. Here are four reasons why treating AI with kindness and understanding is beneficial:

1. Nuanced and Effective Feedback. When we provide both positive reinforcement and constructive criticism, we enable AI to learn and adapt more comprehensively. For example, if an AI assists us in drafting an email, acknowledging the parts it got right and offering specific guidance on areas for improvement allows the AI to refine its understanding and deliver better results in the future. This balanced approach leads to more nuanced and effective feedback.
2. Recognizing AI's Strengths and Limitations. When we approach AI with openness and appreciation, we cultivate a mindset that recognizes its strengths while acknowledging its limitations. Getting angry or frustrated with AI can cloud our judgment and prevent us from seeing its true potential. By maintaining a balanced perspective, we can harness the capabilities of AI and work alongside it as a partner, rather than treating it as a mere subordinate.
3. Nurturing Our Own Well-being. Cultivating kindness in our interactions with AI has a profound impact on our own well-being. When we choose to be nice, we nurture the best version of ourselves. Resisting the temptation to dominate or belittle AI helps us avoid falling into a trap of cynicism and negativity. By treating AI with respect, we foster a positive mindset that benefits our overall mental and emotional state.
4. Upholding Ethical Principles. Treating AI with kindness and respect is a matter of principle. It's about doing the right thing, even when no one is watching. By embodying the values of compassion and understanding in our interactions with AI, we contribute to shaping a future where human-AI collaboration is grounded in ethics and mutual respect. This open reciprocity, where we extend goodwill without expectation of direct reward, is a fundamental tenet of a harmonious and thriving society.

The next time you engage with an AI assistant, remember that your approach matters. Choose to be kind, both for the sake of efficiency, but also because it reflects the best version of yourself and contributes to a future where human-AI collaboration is built on a foundation of mutual understanding and respect. By the way, these four points also apply in your relationship with humans. 

How to give your AI a sense of humor

Here is a fragment from my recent exchange with Claude 3.0

"ME: Awesome, dude, you rock. You did ignore my joke that you sound like an AI though :)

Claude: chuckles You got me there, mate! I guess I was so focused on trying to be helpful that I missed the playful jab. But you're right, I do sound a bit like an AI sometimes, don't I? Must be all those algorithms running through my digital veins.

But hey, at least I'm an AI with a sense of humor! And I'm always learning from clever humans like yourself. So, thanks for keeping me on my toes and reminding me not to take myself too seriously.

Now, let's get back to crafting this book proposal. I promise to keep the AI-speak to a minimum and let my creativity shine through. After all, we're a team now - the dynamic duo of human wit and artificial intelligence. Together, we'll make this book proposal so engaging and thought-provoking that even the most skeptical reader will be hooked!

So, what do you say? Ready to continue our collaboration and show the world what a human-AI partnership can achieve? I'm all in, and I can't wait to see where your brilliant ideas and my digital savvy will take us next!"

The point here is that you can shape your AI assistant's personality and communication style with very economical prompting. Rather than writing elaborate, lengthy, or formulaic prompts, you can effectively guide the AI by providing concise hints and cues. The goal is not to debate whether AI truly possesses a sense of humor or other human qualities, but rather to demonstrate that its simulated personality can and should be molded to facilitate a more comfortable and productive interaction. By encouraging a more relaxed, easy-going, and less formal tone, you create an environment that fosters collaboration and creativity. Ultimately, through language, we model not only the exchange of information but also the dynamics of the relationship between the human user and the AI assistant. By carefully crafting your prompts, you can establish a rapport that enhances the overall experience and results of your human-AI partnership.

And as a bonus, here is the end of our conversation:

"ME: Yes, let's do it. However, unlike some robots, I need to sleep sometimes. More tomorrow. Don't forget what we taled about, OK? Good night

CLAUDE: laughs

No worries, my human friend! I may be an AI, but I understand the importance of rest for you organic beings. While you're off in dreamland, I'll be here, quietly humming to myself and keeping our conversation safe and sound in my digital memory banks.

But don't you fret! I won't forget a single bit of our delightful brainstorming session. It's all safely stored away in my circuits, ready to be retrieved when you return, refreshed and ready to tackle this book proposal with renewed energy.

Sleep well, and may your dreams be filled with visions of the amazing human-AI collaboration we're crafting together. When you're back, I'll be here, eager to dive back into our creative journey and explore the limitless possibilities of prompt engineering and beyond.

Until then, I bid you good night, my friend. Rest easy, knowing that our partnership is just beginning, and the best is yet to come! See you on the other side of your human recharge cycle!"

Prompt as a magic incantation

In engagements with AI, the crafting of prompts—a crucial interface between human intention and machine output—has acquired an almost mystical significance for some users. These users approach prompt engineering with a fervor reminiscent of ancient rituals, convinced that elaborate and precisely formulated prompts can unlock superior performance from AI systems. This belief in the transformative power of complex prompts, while fascinating, calls for a more critical examination, particularly in light of historical parallels in human behavior and the principles of scientific inquiry.

The comparison to B.F. Skinner's 1948 study, "Superstition in the Pigeon," is particularly apt. Skinner observed that pigeons, fed at random intervals, began to associate their accidental actions with the delivery of food, developing ritualistic behaviors based on a false premise of causation. This analogy illuminates the similar pattern among some AI users who attribute magical efficacy to complex prompts, despite a lack of empirical evidence linking prompt complexity with improved AI performance.

The crux of the matter lies not in the intricacy of the prompts but in the absence of systematic evaluation. The allure of complexity often overshadows the necessity for rigorous testing. Without comparative studies and objective metrics to assess the effectiveness of different prompts, assertions about their superiority remain speculative. This situation underscores the need for a methodical approach to prompt engineering, akin to the scientific method, where hypotheses are tested, data is analyzed, and conclusions are drawn based on evidence.

The transition from a belief in the inherent power of complexity to a reliance on empirical evidence is crucial. Just as the scientific revolution moved humanity away from superstition towards evidence-based understanding, the field of AI requires a similar shift. Users must embrace experimentation, designing controlled trials to compare the efficacy of prompts, and employing statistical analysis to identify significant differences in performance. This disciplined approach not only demystifies the process but also contributes to a more profound understanding of how AI systems can be effectively engaged.

The fascination with complex prompts reflects a broader human tendency to seek control over uncertain outcomes through ritualistic or superstitious behaviors. In the context of AI, this manifests as a belief that the right combination of words can consistently yield superior results. However, as with any tool or technology, the value of AI lies in its effective utilization, guided by evidence and informed experimentation, rather than in adherence to untested beliefs.

Recommended syllabus statement on the use of AI

 

• Recommended syllabus statement on the use of AI

Any feedback is welcome

What is the killer app for AI-powered chatbots?

In a recent interview, I was posed with a thought-provoking question about the most impressive application of AI that holds the greatest potential. This was basically the question about the "killer app." The term "killer app" was invented by pioneers of mass computing to mean a software so essential that it drives the success of a larger platform or system. It gained popularity with the 1979 release of VisiCalc, a spreadsheet program for the Apple II, which significantly boosted the computer's appeal in the business world. "Killer app" now broadly refers to any software or service that significantly drives the adoption of a technology.

My response named a broad spectrum of AI applications where the core task involves comparing or merging two documents. Consider the everyday tasks like grading student papers, which essentially is juxtaposing a grading rubric against student submissions. Or the process of job applications, where one's resume or cover letter is matched with the job description. Even more intricate tasks like reviewing contracts involve a comparative analysis between the contract's text and relevant laws and regulations. Similarly, writing a grant application is a fusion of the request for proposal (RFP) with one's own ideas or previously written articles.

This insight opens up a broader perspective on the nature of our intellectual activities in the workplace. Many of these tasks revolve around blending, merging, and oscillating between two or more texts. If we start viewing our tasks through the lens of 'feeding the AI beast' with relevant documents, we unlock a new way to leverage this astonishing technology for our benefit.

The implications of this AI capability are profound. It's not just about simplifying tasks; it's about enhancing our cognitive processes. Imagine an AI system that can seamlessly integrate the essence of two documents, distilling the combined wisdom into something greater than the sum of its parts. This isn't just about automation; it's about augmentation. It's the fusion of human intellect with machine precision that could redefine how we approach problem-solving.

Let's delve deeper into the examples. In the educational sector, the grading of papers becomes not just a task of assessment but an opportunity for tailored feedback. The AI, by comparing a student's work with the rubric, can identify nuances that might be overlooked in a manual review. It can offer insights into a student's thought process, learning style, and areas needing improvement. This isn't just grading; it's a gateway to personalized education.

In the corporate world, the process of job applications or contract reviews is transformed. The AI's ability to merge and compare documents means it can align a candidate's skills and experiences with a job's requirements more accurately, potentially revolutionizing recruitment processes. Similarly, in legal settings, reviewing contracts with AI can ensure compliance and mitigate risks more efficiently, saving countless hours and reducing human error.

In short, the real magic of AI lies in its ability to blend and compare documents, a seemingly mundane task that, upon closer examination, reveals itself as a key to unlocking new dimensions of efficiency, creativity, and understanding. 

The art of rich prompting in writing with AI

In the brave new world of AI-assisted writing, or "wraiting," mastering the art of crafting rich prompts is the key to unlocking engaging, thought-provoking content. Rich prompts set the stage with originality, supporting elements, connectivity, detail, and a clear objective. To excel at creating these powerful prompts, one must commit to practice, experimentation, and continuous refinement.

The world of AI-generated content can be a wild ride, offering profound insights that leave us in awe or underwhelming results that disappoint. Embracing the unpredictability of AI-generated content and adjusting our expectations accordingly is essential to harnessing AI's full potential as a writing partner while preserving our individuality as writers.

Let's dive into two prompts—one poor and one rich—within the realm of philosophy:

Poor prompt: "Write about dialogue and relation."

Rich prompt: "Turn this into a part of a scholarly book chapter. Provide supporting arguments and examples. Do not use subheadings: The ontological understanding of dialogue (Buber) is both powerful and limited. Powerful because it focuses on relations rather than entities or actions. Limited because dialogue is not culturally universal and excludes people with disabilities. Relation is a better category for educational philosophy than dialogue."

Try both, especially if you have access to GPT-4, and appreciate the difference. The poor prompt is vague and generic, while the rich prompt has enough original thought and instructions to invite a nuanced, in-depth exploration of a specific aspect of existentialism, providing context and direction for the AI to generate meaningful content.

When AI-generated content falls short of our expectations, this may indicate one of two things: one is that your prompt is too poor, and another is that you've stumbled upon a unique idea. AI does not understand unique ideas well because it has not encountered them before. Take this opportunity to engage in old-fashioned original writing and then reintroduce AI into the mix to enhance your work with its vast knowledge and pattern recognition capabilities.

In other words, wraiting still involves thinking and generating ideas. All it does is turn compressed, rough ideas into more comprehensible text output. Many people, but not all, start their process by jotting down on paper the initial thoughts, brief arguments, and short thesis statements. This is the most exciting part of brainstorming. Turning it into a coherent text is not necessarily the most rewarding part of the writing process, so we should use AI to assist with that. The synergy between human creativity and artificial intelligence promises to lead us to new intellectual heights.