A Lifetime Chat History with Chatbots Could be a Valuable Resource You Could Start Building Today

I have recently given some thought to using an AI chatbot or a large language model (such as ChatGPT) for a friend. If a chatbot could behave in just the right ways, I might prefer it to a human. I started thinking about this after reading very positive reviews from people who have used AI for friendship or therapy. Those reviews influenced me to try out a few of the popular AI companion apps like Replika and Anima. I was only slightly impressed. They work well, but it seemed like they would only appeal to people who were lonely. I felt no camaraderie or attachment, and I didn't feel like I was building anything lasting.

I realized that a chatbot could capture my interest and attention if it provided an additional benefit: long-term memory. Spending a few minutes with a chatbot daily would be worthwhile if it could save and catalog all the conversations in a permanent, ever-expanding file. In this post, I will explain how an AI could index this conversational data and make meaningful references to it.

 

First, let's use the following list to start thinking about the role a chatbot could play in our lives. As you do this, consider how an ability to recall previous interactions would make its contributions more powerful.

 

Roles That an Intelligent Chatbot Could Play in Your Life

 

Friend / Companion / Confidant

Record keeper / Scribe / Diary / Journal / Notebook / Planner 

Assistant / Secretary / Employee

Muse / Coauthor / Research Assistant / Co-investigator

Autobiographer

Therapist/ Psychologist / Psychiatrist

Doctor / Primary Care Practitioner

Counselor / Coach

Romantic Interest / Life Partner

Avatar of a Historical Figure or Deceased Loved One

Board Room / Interest Group / Review Panel / Focus Group

Lawyer / Judge / Arbitrator / Mediator / Private Legal Counsel

Advisor / Role Model / Hero 

 

A Chatbot History Would Greatly Augment Your Long-term Memory

 

If a chatbot could save all your conversations with it into a database, then it could mine that data for useful purposes. Because it consists of words, it would have a very small file size. With modern neural network tech, it could be queried rapidly. As humans, we are constantly forgetting meaningful things. A chatbot history would be able to fill in gaps. For instance, sometimes I can't remember the details about an idea, objective, or intention I held, or the memories it was tied to. This record could help you bridge your memory lapses and answer questions that you have about your life in specific or yourself in general. You could ask the bot about previous long-forgotten comments, anecdotes, and thought patterns. It could record and catalogue your inspirations and epiphanies better than you ever could. 

If you used it regularly for years, the bot could get to know you better than you know yourself. This would be amazing, especially because its purpose would be to serve you with that very information. It could build a narrative about who you are as a person. It could easily flesh this out into an autobiography or memoir. 

    

Research, Collaboration, and Productivity

 

Aside from just talking idly, we could actively and systematically pick a chatbot's brain and bounce ideas off it. Major language models are already connected to the internet. In a few years, they will be especially good at searching for knowledge, distilling it, and packaging it into concise, comprehensible answers to our questions.

 

A chatbot with your chat history should be designed to help you record and build on your ideas. It should help you fact-check and explore your hypotheses, giving you the scientific and academic information you need to elaborate on them. It should give you expert feedback, find evidence for your claims, and help substantiate your arguments. It should ask you the questions needed to flesh out your proposals, helping turn your ideas into essays or books.

 

It is not easy to gather your ideas in an effort to write a professional treatment on a topic. I had to use journals and notebooks extensively to create the articles I have published. I would go as far as to say that I could not have done it without them. I could not have cohesively spelled out my theories without external memory tools like computer files, word processing software, and good old pen and paper. But an expertly curated chat history would be much more powerful than these.

It is incredible how simply taking notes about your thoughts and regularly reviewing and editing them fosters the growth of those ideas. If I had a chatbot assistant available to me starting in my late teens, I would've been much more productive and would've been able to generate far better insights.

 

As hunter-gatherers, our brains were not meant to compile text or prose and recall it on demand. Many of us are too lazy or busy or indisposed to sit down and transcribe our thoughts letter by letter. Dictating it to a chatbot and then letting the chatbot file it away in the most relevant location, in the right document or folder, would be much easier. Then it would help us retrieve it when needed. I often cannot locate notes that I have taken. Finding them can be made easier by the search function in Microsoft Word or Windows. But a chatbot with the right access would be able to perform a global semantic search on all of your files with much more specificity.  

 

 

An Intimate Record of Our Daily Lives

 

We are often proud to share our insights with our friends, but our friends forget the points we made, and often so do we. A chatbot with long-term memory would never. And a good one wouldn't let us forget the important insights.  

 

A comprehensive digital record of all chatbot interactions could be valuable in many domains. You might insert this file (or an edited, condensed, or censored version) into different systems when you interact with them so they can better understand you and interpret your behavior. This record would make a chatbot better at being your therapist and counselor (imagine visiting different AI psychologists, where each one was aware of every comment you ever made in therapy). It would make for a more competent and personalized assistant and productivity guru. It would make feedback from a virtual yoga instructor, dietitian, or personal trainer more informed and detailed. It would make an AI's observations as a critic more insightful and recommendations as a life coach more viable.

 

If you asked for complete confidentiality, it would give it to you. And if you ever asked it to forget something and strike any digital memory of it from storage, it would. We could ask a chatbot to record conversations with other people if we can get those people’s permission. This would mean that text messages, phone calls, and emails could be added to the chat history. We could even have a device such as our phone record everything we do all day and add this to the record. Clearly, however, you can see that it will be important for the system to be able to search for and redact comments that could could jeopardize privacy. 

 

One of my favorite things in life is when a friend reminds me of something I had long forgotten. Now that I'm in my 40s, I relish nostalgic moments. I search them out actively, such as by scouring streaming services for old movies and music or searching eBay for toys from my childhood. But I'm running out of things to give me that nostalgic feeling. A lifelong chatbot friend could provide this on demand. Those intimate and touching thoughts and feelings that our cerebral cortex can no longer retrieve would again be available. 

 

We already have an internal monologue that runs ceaselessly throughout the day. Recording its ideas a few times an hour, simply by having a conversation with a robotic pal, would be little work. Especially if it pulls the information out of us by asking us engaging questions. Also, once we come to expect and rely on this chatbot service, we will uncover methods to use it more efficiently and put its record to work in different ways that are unforeseeable to humans today.

 

Begin Merging with a Superintelligence Today

 

I cannot wait to hold conversations with a form of artificial general intelligence (AGI). I eagerly anticipate interrogating it, learning about how it thinks, and hearing its insights into the mysteries of the universe. Unfortunately, super-intelligent AI may be decades away. But if, in the interim, I create a log of my interactions with its predecessors, it could use that log to better understand and relate to me. The chat record would immediately tell the AI what I'm interested in and what avenues I would like to learn more about. It would inform it how best to efficiently explain things to me.  It would also allow it to become like an old friend after the milliseconds it would take to read and process the entire conversational history. Any advanced AGI system could come to know you immediately and intimately. In other words, the best way to prepare for our future interactions with AGI is to start recording our interactions with chatbots.

 

Prompting The Chatbot

 

Language models have something called an attentional window (a.k.a. context window). This holds the prompt that you write when you ask it a question but can only hold so many words. It is also capable of holding the last few prompts you gave it and this is how it can refer back to an earlier point in your conversation. Most commercially available language models reset this conversation history after just a few exchanges. When the window is reset, the content is gone forever, as if it never happened. 

Currently, Microsoft and OpenAI reset the context window to keep GPT from being manipulated by multiple prompts intended to influence it to fly off the rails. However, the context window for chatGPT is around 4,000 tokens (tokens are comparable to words), and the window for GPT-4 is up to 32,000 tokens. Right now, some large language models' attentional window is large enough to encompass a large book. That is very large. This allows a model to actively consider every sentence in an entire book, along with your prompt, when it formulates a response. Instead of placing a book in its attentional window, you could place your chatbot transcript. That's right. This would allow the chatbot to consider every word of your meaningful interactions with it over many years every time it responds to you. This would permit it to remember, and be influenced by, the exact context of every line of conversation you ever had with it. This technology is improving rapidly and you can imagine the degree of specificity and nuance that such systems will soon be capable of.

 

Using alternate forms of storage, such as vector databases, could greatly augment this attentional window. Vector databases may not be necessary because your chat transcript would be tiny, never even entering into the gigabyte range. For instance, the size of all the article text in the English Wikipedia was only 1 GB in 2006. But vector databases can be used for other purposes. They can help the system to categorize prompts and conversations (embedding them in multidimensional semantic space). The next time the user brings up a certain topic, that topic will be matched against the vector database, to locate and fetch the 10 to 20 most similar or relevant previous conversations so that they can weigh more heavily in the attentional window during inference (response generation).

The system could also improve your short-term memory by helping you stay on track once you reach an exciting area of inquiry. Its immediate and perfect memory caches for words would keep you from forgetting what you were just discussing with it. It could also nudge you to talk about productive things and to focus with greater intent on your pet theories. 

 

Exporting Your Chat History

 

Right now, we can start recording our dialogue with language models like chatGPT. To do so, we must manually copy and paste the messages from our internet browser to another file such as a Word document. This is because, today, most chatbots don't offer to keep a written transcript of the discourse. However, we can expect that language models will always be able to receive and operate on such long transcripts, so maybe we should start copying and pasting now.

 

An AI agent that maintains a transcript of all previous conversations and actively uses the data will be marketable and lucrative. As consumers, we should demand the ability to export the transcript of our conversations so that we can import them to other chatbots. This will ensure that we can use it with the offerings from multiple companies. It will also ensure that the companies engineering the bots will compete at making the use of this conversational history more relatable and useful. Each company will have a proprietary way of analyzing the transcript to mine for topics of conversation. This transcript may end up being actively transferred and updated between chatbot companies behind the scenes, like a type of user ID, becoming a component of our digital fingerprint and digital footprint.

 

Embellishing Your Digital Avatar

 

A history of conversations with chatbots will allow people to embellish avatars of themselves. Now, with the capability of deep-fakes, there is a growing interest in creating avatars. People are creating avatars that will live on after they die or memorialize family members that have passed away. Incorporating a dossier, with years of personal conversations, would make a much more comprehensive avatar. 

 

Historians wish they had more data on historical figures. They also wish they had more data on everyday people of the past. Psychologists wish they had more data on humans, their decisions, beliefs, and thinking processes. I wish I had more data on who I was as a child, what I believed in my adolescence, and how I became the person I am today. A chatbot with long-term memory could make all this possible. 

 

The bot should do its best to get to know you deeply and to understand the real, authentic you. This rich interplay with yourself could help you discover who you really are. It could ask thousands of incisive questions that could help it model you with more fidelity and understand you with more accuracy. This would further customize the interaction. In doing so, it should counsel you supportively and empathically, challenge your shortcomings, aid your personal development, and offer unconditional positive regard. Its goal should be to help you become self-actualized, with clarified values and heightened introspection. I am excited about building an intimate archive of this cooperative journey through life. 

I asked GPT-4 the following question:

“Why would it be helpful for a chat bot to have a complete history of all previous conversations with a user?”

This was its reply:

“A chatbot can benefit from having a complete history of all previous conversations with a user for several reasons. Some of them are:

• A chatbot can use the history to personalize the interaction and provide more relevant and tailored responses. For example, a chatbot can remember the user’s name, preferences, interests, and previous requests and use them to create a more engaging and satisfying experience1.
• A chatbot can use the history to learnfrom the feedback and behavior of the user and improve its performance over time. For example, a chatbot can analyze the user’s satisfaction, sentiment, and engagement levels and adjust its responses accordingly. A chatbot can also use machine learning techniques to generate new responses based on the data collected from the history1.
• A chatbot can use the history to resolveissues and queries more efficiently and accurately. For example, a chatbot can access the user’s transaction history, order status, account details, and previous complaints and provide faster and more reliable solutions. A chatbot can also use the history to avoid repeating the same information or asking the same questions234.

These are some of the benefits of having a complete history of all previous conversations with a user for a chatbot. Do you agree with them? 😊”