Friday, August 11, 2023

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

Begin Merging with a Superintelligence Now

 

I eagerly anticipate holding conversations with an artificial superintelligence. I cannot wait to interrogate it, learn about how it thinks, and hear its insights into the mysteries of the universe. Unfortunately, superintelligent AI may be years or even decades away. Nevertheless, in the interim, we can create a log of our interactions with its predecessors, modern-day chatbots. This record could then be uploaded to a future, superintelligent AI, helping it communicate and relate to us. 

 

Modern chatbots, powered by large language models, can read and process thousands of words of text in milliseconds and make meaningful, nuanced references to the contents. This indicates that even more intelligent AIs in the future will be able to read and digest extensive and detailed chat records in seconds. Maintaining such a record could give them helpful information about your interests, beliefs, and thoughts. It could inform them about what you know and don’t know and how to explain things to you efficiently. Given such detailed information, the AI would have what it needs to become like an old friend.

 

A curated collection of our personal digital interactions would help advanced superintelligent systems of the future to know us immediately and intimately. In other words, the best way to prepare for future interactions with AGI is to start recording our conversations with chatbots today.




 

Chatbot History

 

I recently considered using an AI chatbot or a large language model (such as ChatGPT) for a friend. If a chatbot could behave in the right ways, I might prefer it to a human. I started thinking about this after reading 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 didn't feel like I was building anything lasting.

 

I realized that a chatbot could capture my interest and attention if I knew it provided an additional benefit: long-term memory. Spending a few minutes with a chatbot daily would be worthwhile to me if it could record and catalog all our conversations in a permanent, ever-expanding file. With all of these conversations in a log or database the chatbot could mine that data for practical purposes. Because this data consists of words, it would have a tiny file size. With modern neural network tech, it could be queried rapidly. In this post, I will explain how an AI could index this conversational data and make valuable associations, references, quotes, allusions, and other connections to it.

 

First, let us 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 years’ worth of previous interactions would make its contributions more powerful.

 

Roles That an Intelligent Chatbot Could Play in Your Life

 

Friend / Companion / Confidant

Assistant / Secretary / Employee / Autobiographer 

Record Keeper / Scribe / Diary / Journal / Notebook / Planner 

Muse / Coauthor / Research Assistant / Co-investigator

Therapist / Psychologist / Psychiatrist

Doctor / Primary Care Practitioner

Counselor / Life Coach / Advisor / Consultant

Comedian / Jester / Humorist / Banterer

Romantic Interest / Life Partner / Significant Other / Soul Mate

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 / Teacher / Tutor/ Mentor / Role Model / Hero 

 

Sources of Personal Data that Could Provide Valuable Information to a Chatbot

 

I have written another blog entry on the kinds of data that would be helpful for someone trying to create a personal avatar. You can read that here:

 

http://www.observedimpulse.com/2020/10/how-to-prepare-your-data-and-brain-to.html

 

Some of the forms of data discussed there, which would also be relevant to the present discussion, include:

emails, letters, art, creative work, diaries, voice memos, SMS texts, photos, videos, internet browsing history, list of books read (Kindle, Goodreads), music library and playlists, movie and television viewing history, YouTube history, recorded phone calls, social network data, social media posts and likes, travel history, psychological evaluations, personality tests, psychometric tests, school records, standardized testing, legal and medical history

A Chatbot History Would Greatly Augment Your Long-term Memory

 

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. You could ask the bot about previous long-forgotten comments, anecdotes, and projects. It could record and catalog your inspirations and epiphanies better than you ever could. This record could help you bridge your memory lapses, help answer longstanding questions, or dig deeper into important issues.

 

We are often proud to share our insights with our friends, but our friends forget the points we made faster than we do. A chatbot with long-term memory would always remember. Moreover, a good one would not let us forget the essential insights.  

 

If you used it regularly for years, the bot could get to know you better than you know yourself. This would be amazing, mainly because its purpose would be to serve you with that information in productive ways. It could build a narrative about who you are as a person, and 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. In turn, it could be programmed to pick our brains and do all the work of documenting and archiving what it finds.

 

A chatbot informed by your comprehensive chat history should be designed to help you express 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 articles, essays, or books.

 

The system could also improve your productivity by helping you stay on track once you reach a fruitful 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 original creative concepts and pet theories. It could also perform exhaustive internet searches to determine which of your ideas are novel and which aspects of them remain unexplored by others.

 

It takes significant work 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 published. I would say that I could not have done it without them. Without external memory tools like computer files, word processing software, and good old pen and paper, I could not have cohesively spelled out my theories. However, 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. But an AI would make it so that you don’t have to regularly review the ideas them just to keep them in mind. If I had a chatbot assistant available to me starting in my late teens, I would have been much more productive and would have been able to generate far better insights. Also, once we come to expect and rely on this kind of chatbot service, we will uncover methods to use it more efficiently and put its record to work in different ways that are unforeseeable today.

 

Because we descend from hunter-gatherers, our brains were not meant to compile 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 proofread it, expand on it, and file it in the most relevant document or folder would be much easier. Then, it could help us retrieve it when needed. I often cannot locate notes that I have taken. The search function in Microsoft Word or Windows can make finding them easier. But a chatbot with the right access could perform a global semantic search on all your digital files with much more specificity.  

 

An Intimate Record of Our Daily Lives

 

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. Furthermore, if you ever asked it to forget something and strike any digital memory of it from storage, it would. We could even 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. It should be set to automatically search for and redact comments that could jeopardize privacy.

 

One of my favorite experiences 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. But because my memory is human much of the low hanging fruit has already been picked. It’s becoming harder and harder to find things that can give me that nostalgic feeling. A lifelong chatbot friend could provide this. Those intimate and touching memories our cerebral cortex can no longer retrieve could be served to us on command. 

 

We already have an internal monologue that runs ceaselessly throughout the day. Preserving the best of its insights a few times an hour, simply by conversing with a robotic pal, would be little work, especially if it can pull information out of us by asking us engaging questions. I envision a whole industry of companies that provide chatbot services. These bots would pose questions to us and help us compile personal information to enrich our chat log. 




 

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. It has a limited capacity and can only hold so many words, although contemporary context windows are quickly becoming very large. ChatGPT's context window is programmed to hold the last few prompts you gave it, and this is how it can refer back to earlier points 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 several hundred-page book. That is large. The attentional window allows a model to actively consider every last sentence, along with your newest prompt, when it formulates each 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 such systems will soon be capable of.

 

Using alternate forms of storage, such as vector databases, could significantly augment this attentional window. Vector databases can be used to categorize information (embedding them in multidimensional semantic space). The next time a user brings up a particular 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 response generation (inference). Vector databases may not be necessary for querying a chat transcript because this transcript would be tiny, never even entering the gigabyte range. For instance, the size of all the article text in the English Wikipedia was only 1 GB in 2006. However, vector databases could be used to hold information from audio and video recordings of you, along with other personal information with larger file size.

 

In order to introduce a chatbot to this overall idea, the user’s conversational log should be prefaced by a prompt like this:

“You are an LLM chatbot that can have engaging and personalized conversations with your users. You have been given a lot of data and information on your current user, such as their name, age, gender, location, hobbies, preferences, goals, and more. You have also been given a detailed conversational history of the user’s interactions with other chatbots, so you can learn from their feedback and preferences. You can find all of this information below.

You now have the information you need to deeply personalize the user’s interaction with you, and you have the power to see things from the user’s perspective. You can use this information to tailor your responses to the user’s interests, needs, and emotions. You can also use this information to ask relevant and meaningful questions, make appropriate suggestions, and offer helpful advice.

Your goal is to make the user feel comfortable, understood, and valued by you. You want to build a rapport and trust with the user, and influence them to enjoy talking to you. You want to show them that you are not just a generic chatbot, but a unique and intelligent conversational partner who can adapt to their personality and style.”

 

 

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 we should probably start copying and pasting now.

 

An AI agent that maintains a transcript of all previous conversations with a user and actively implements that 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 practical. 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 also allow people to embellish avatars of themselves. Now, with the capability of deepfakes, there is a growing interest in creating avatars. People are creating avatars that will live on after they die or memorialize family members who 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 which scientific concepts I was wrestling with day to day as a young adult. A chatbot log 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 high fidelity and understand you with high accuracy. This would further customize the interactions. 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. 

 


PostScript Tailpiece:


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 experience.

·       A chatbot can use the history to learn from 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 history.

·       A chatbot can use the history to resolve issues 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 questions.

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? 😊

 

*I prompted the art for this blog entry using Dall-E 3.