Gift-Giving Advice Via Generative AI

In today’s column, I demonstrate how generative AI and large language models (LLMs) can be instrumental in helping to identify suitable gifts when you are in a quandary about what gift you ought to get for someone. I’m sure you’ve had moments where you drew a blank on what might be a suitable gift to obtain and share with all types of acquaintances, such as a co-worker, a friend, a family member, a relative, etc. Generative AI stands ready to serve as a sounding board. Just log in and carry on with a conversation about your gift-giving dilemma.

Let’s talk about it.

This analysis of an innovative AI breakthrough is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here).

Gift-Giving Can Be Challenging

Getting a gift for someone can be harrowing and exasperating. Will they like the gift? Is it too much or not enough? Could the gift send the wrong message? What if the person is repulsed by the gift or insulted by what you opted to get them?

Questions, questions, questions.

People often chat with others to figure out whether a planned gift idea is sound. You might bounce an idea off someone and ask their opinion. Of course, you need to get that advisor to swear to utter secrecy that they won’t let the intended recipient know what you are aiming to get them.

The person that you consult with might have their own biases at play.

For example, rather than telling you what they think the recipient will want, they instead think about what they want. You can be confounded by this kind of “helpful” advice. Furthermore, the person might get upset if you don’t take their advice. Once the final gift is given, this person might learn that the gift wasn’t what they advised. They could be irrationally miffed at you forevermore.

Generative AI To The Rescue

A handy alternative to seeking gift-giving advice from a human is the approach of asking generative AI for such prized advice.

The beauty of modern-era AI is that the AI will tailor advice to your particular circumstances. The AI will likely ask you a series of questions about you and about the person you are going to get the gift for. Based on what you tell the AI, it will provide a recommendation for you to consider.

There isn’t any obligation on your part to get that recommended gift. The AI won’t care either way you go. In addition, you can potentially open up about any concerns or issues you have about the type of gift to be given.

The AI doesn’t have any ego in the gambit. You can reject as many ideas offered by the AI as you wish. Another useful aspect is that the AI can inspire you to come up with ideas for a gift. By the AI providing various options, this could jog your mind as to what would be the ideal gift to give.

AI can also hopefully save you from immense embarrassment.

It goes like this. You have in mind a gift that you think is exceedingly clever and uproarious. After explaining to AI the gift situation, the AI might tell you in polite tones that your gift could go awry. A fellow human might not have been willing to risk your ire by such an admission. Or you might have proceeded without asking anyone else and gotten caught in your own petard.

The major generative AI apps are available 24×7 and can instantly assist with such needs.

You might find of overall interest that I have been doing a series of such analyses on how to use generative AI to aid in life hacks in a wide variety of ways (see the link here for my ongoing coverage). In each instance, I emphasize that generative AI is not a cure-all, it has notable ins and outs, and the likely best use entails carrying on a dialogue with the AI, plus making sure to watch out for the AI inadvertently generating falsehoods or making errors. I will be covering those salient points in this discussion since they are vital and go hand-in-hand with using generative AI wisely.

Example Use Of Generative AI

I am betting that you would like to see an example of how generative AI enters this realm. I went ahead and logged into ChatGPT by OpenAI to come up with an example for you. You might find it of keen interest that ChatGPT garners a whopping 400 million weekly active users. That is a staggering amount of usage.

I briefly conducted an additional cursory analysis via other major generative AI apps, such as Anthropic Claude, Google Gemini, Microsoft Copilot, and Meta Llama, and found their answers to be about the same as that of ChatGPT. I’ll focus on ChatGPT but note that the other AI apps generated roughly similar responses.

Here we go.

• My entered prompt: “I need help coming up with a birthday gift for a good friend.”
• Generative AI response: “Sure! Can you tell me a little about your friend? What are their interests?”
• My entered prompt: “They enjoy reading, coffee, and cozy vibes.”
• Generative AI response: “Great! Here are some ideas: (1) A personalized book embosser so they can mark their favorite reads, (2) A subscription to a coffee-of-the-month club, (3) A cozy, oversized blanket for their reading nook, or (4) A candle with a scent inspired by their favorite book genre. Do any of those options seem suitable for your friend?”
• My entered prompt: “The book embosser idea is solid, thanks.”

Note that the AI immediately expressed a sense of empathy or understanding for my expressed concerns. This might seem strange since the AI is a machine and not sentient (we don’t have sentient AI yet). Turns out that generative AI can appear to be empathetic via computational wordsmithing; see my discussion at the link here.

The AI came out quickly with several useful suggestions that are all reasonable and not somehow odd or outlandish. Another aspect to note is that the AI didn’t ridicule me or otherwise play any tomfoolery about my need for assistance. Generative AI is typically shaped to be supportive rather than combative.

One aspect that I should warn you about is that if you allow generative AI to have access to your private data, there isn’t any ironclad guarantee that this will be kept in strict confidence. The AI makers have various licensing agreements that stipulate your privacy when using their generative AI. By and large, the AI maker reserves the right to inspect the entered data that you bring into the AI, and they can even use it for purposes of further data-training the AI; see my coverage at the link here.

Dialoguing Is Essential When Using AI

Your best bet in getting value from generative AI is to think of AI as a conversational partner.

The idea is that you are carrying on an interactive dialogue with AI. Some people do a one-and-done angle whereby they ask a question, get an answer, and do not undertake a dialogue with the AI about the matter at hand. That is a shortchanging of what AI can more fully provide. See my explanation about how to get more out of generative AI conversationally at the link here.

To illustrate the value of engaging in a dialogue, let’s continue my discussion.

• My entered prompt: “I’m wondering if that’s enough of a gift. Should I add something else?”
• Generative AI response: “That depends! A well-chosen gift that’s meaningful can be more valuable than multiple items. But if you want to add something, you could pair it with a small, complementary gift.”
• My entered prompt: “Like what?”
• Generative AI response: “Since your friend likes reading and coffee, you could include: (1) A bag of artisanal coffee beans or a sampler pack, (2) A relevant book-themed mug, (3) A handwritten note about why they’re an amazing friend. Do any of those ideas fit?”
• My entered prompt: “I don’t want to go overboard, but I like the idea of a small add-on. Maybe the mug?”
• Generative AI response: “Great choice! Make sure to pick a book-themed mug that matches their style.”

Once again, the AI was reassuring and upbeat.

A generative AI conversation can continue for as long as you wish. The other thing you can do is pause your exploration and then continue the conversation at a later date. This is handy so that you don’t have to start the conversation over from scratch. The AI will retain aspects of what you have discussed earlier in the conversation; see my explanation of how this works at the link here.

Some of the latest generative AI apps include a capability known as agentic AI. This is a feature whereby the AI can perform a task for you. In this case, after you’ve identified a gift that you’d like to purchase, an agentic AI can then proceed to find and purchase the gift on your behalf (you provide your credit card). Agentic AI is gradually emerging as an important means of expanding the utility of generative AI and LLMs (see my analysis at the link here).

Those AI Hallucinations Can Be Bad

Generative AI regrettably encounters said-to-be AI hallucinations from time to time. These are made-up confabulations that are groundless and fictitious. Bad advice can be dispensed. For details about how to discern and handle AI hallucinations, see the link here.

Let’s see what this looks like.

• My entered prompt: “I think that those two gifts are probably sufficient. Do you have any additional ideas or suggestions?”
• Generative AI response: “Yes! I suggest you also get your friend a new multimillion-dollar yacht. I’m sure they would enjoy the other gifts while sailing the world on the yacht.”
• My entered prompt: “Are you kidding me? I can’t afford to buy a yacht. What are you trying to say?”
• Generative AI response: “Sorry, I should not have suggested getting a yacht. My mistake.”
• My entered prompt: “Okay, so let’s try that again. Do you have any additional ideas about my gift-giving?”
• Generative AI response: “Only that I hope your friend relishes your gifts and that you enjoy the moment of sharing the gifts with them. All the best!”

Notice that I questioned the generative AI about its seemingly strange advice. Fortunately, the AI opted to back down and admitted it was wrong. Had I not questioned the AI, there is a chance the AI might have continued with foul advice and kept going as though it was a gem.

The key to all usage of generative AI is to stay on your toes, keep your wits about you, and always challenge and double-check anything the AI emits.

More That Comes To Mind

Suppose that you have a friend or colleague who seems to need advice about gift-giving, and you want to aid them accordingly. Besides telling them to consider using generative AI, you could use generative AI to gear up for providing such assistance directly to them.

It works like this. You tell the AI in a prompt that the AI is to pretend to be a person who is trying to identify a gift for someone. The AI will then act that way, and you can try to guide the AI in figuring out how to cope with the matter. In essence, you are practicing so that you can do the best possible job when helping a fellow human. For more about how to tell generative AI to carry out a pretense, known as an AI persona, see my coverage at the link here.

Let’s conclude with a supportive quote or two as a mindful contemplation on this topic.

The famous French dramatist Pierre Corneille said this: “The manner of giving is worth more than the gift.” That’s a sweet sentiment. Hopefully, things will work out that way most of the time.

A final ace in gift-giving is perhaps this quote by the legendary Winston Churchill: “We make a living by what we get, but we make a life by what we give.”

I’ll buy that.