ChatGPT now has a memory - but it's naive

Screenshot - OpenAI

Last year, during the hype surrounding Large Language Models (LLMs), I published a position paper and wrote in this blog that LLMs, like ChatGPT, would need a persistent memory of their conversations to be most helpful. It's tough to converse intelligently with somebody with no memory. We value old friends so much because we know they recall events relevant to us, both good and bad, going back many years or even decades. 

However, managing that memory responsibly is a nontrivial task. Moreover, if virtual assistants based on LLMs become part of our daily lives, as it seems they will, their memory may have to be maintained over many years, perhaps even decades. I don't believe ChatGPT's memory management will be sufficient for this task.

My research has primarily focussed on case-based reasoning (CBR), a memory-based method. Interestingly, as a research community, we didn't consider how our case-bases (the memory) should be maintained over time. This was because we'd been focused on building systems in the early years of the discipline. Only when the systems matured did we realise our memories needed to be maintained. This happened in the late 1990s and centred on the work of Wilson and Leake, for example, "Categorizing case-base maintenance: Dimensions and directions". This work sparked a new line of research within CBR, leading to "Remembering to Forget" becoming a memorable paper title.

Consider this scenario: you've asked ChatGPT to remember your partner's name and that they like dark chocolate. You subsequently break up and acquire a new partner who prefers milk chocolate. You later ask ChatGPT to advise on buying a present. ChatGPT recommends dark chocolate in a gift box. Its memory is out of date, and the recommendation is inappropriate. The event of breaking up with your previous partner should have triggered a memory management process. These triggers are detailed in Wilson and Leake's paper in a comprehensive framework for maintaining memories. 

OpenAI's memory for ChatGPT is described in a FAQ webpage that is naive in its simplicity. The memory is described as a "notepad" with individual memories jotted down sequentially on it. Users can review and delete individual memories. But this is far too simplistic an approach to manage an AI assistant's memory that may have to span many years. An AI Assistant's memory must be structured, and policies and procedures will be required to manage it. OpenAI and others who build AI assistants with long-term memories should draw upon the expertise of case-based reasoners who have been managing memory for decades. Otherwise, they are in danger of reinventing the wheel.

Coincidentally, I've just been reading Why We Remember by Charan Ranganath. This book provides a fascinating insight into how the brain processes memories and highlights how little we currently know about this crucial aspect of ourselves.

Call for Papers: Workshop on CBR and LLMs

Generated by Gemini

Last year was the most remarkable year in AI that I can recall. Large Language Models (LLMs) like Chat-GPT changed the public perception of AI, and what had previously seemed like science fiction was now a reality. I was only tangentially familiar with LLM research, having been working on emotion recognition in speech with a PhD student. However, last year, I started diving into LLM research in-depth, which, as one commentator said, was like trying to drink water from a fire hydrant, such was the volume of publications through places like arXiv.

I view all problems through a lens coloured by case-based reasoning (CBR), my long-term AI research speciality. I quickly saw synergies between CBR and LLMs where both could benefit from each other's approaches, and I wrote up my initial thoughts and published them on arXiv.

CBR has an annual international conference, and I proposed the idea of a workshop at the conference on CBR-LLM synergies to some colleagues, who all thought this was a great idea and agreed to co-organise the workshop with me. The Case-Based Reasoning and Large Language Models Synergies Workshop will take place at  ICCBR 2024 in Mérida, Yucatán, México on July 1st 2024. The Call for papers can be accessed here, and submissions are via EasyChair. 

A Long-term Memory for ChatGPT

Generated by Gemini

In October last year, I published a short position paper, A Case-Based Persistent Memory for a Large Language Model, arguing that ChatGPT and other LLMs need a persistent long-term memory of their interactions with a user to be truly useful. It seems OpenAI was listening because a couple of days ago, they announced that ChatGPT would retain a persistent memory of chats across multiple conversations. As reported in Wired, the memory will be used to add helpful background context to your prompts, improving their specificity to you over time. I argued in my October paper that the LLM community should look to the Case-Based Reasoning community for help with memory since we are the discipline within AI that has been explicitly concerned with memory for decades. For example, we long ago realised that while remembering is vital, a memory must also be able to forget some things to remain functional. This is a non-trivial problem discussed in Smyth and Keane's 1997 paper Remembering To Forget: A Competence-Preserving Case Deletion Policy for Case-Based Reasoning Systems. The synergies between CBR and LLMs will be the focus of a workshop at ICCBR-24 in July in Merida, Yucatán, México.

Intelligent Agents: the transformative AI trend for 2024

Generated by DALL-E

As we move into 2024, the spotlight in AI will increasingly be on Intelligent Agents. As outlined in the influential paper by Wooldridge and Jennings (1995), agents are conceptualized as systems with autonomy, social ability, reactivity, and pro-activeness. Their evolution signifies a shift from mere tools to entities that can perceive, interact, and take initiative in their environments, aligning with the vision of AI as a field aiming to construct entities exhibiting intelligent behaviour.

The fusion of theory and practice in agent development is critical. Agent theories focus on conceptualizing and reasoning about agents' properties, architectures translate these theories into tangible systems, and languages provide the framework for programming these agents. This triad underpins the development of agents that range from simple automated processes to systems embodying human-like attributes such as knowledge, belief, and intention.

Ethan Mollick's exploration of GPTs (Generative Pre-trained Transformers) as interfaces to intelligent agents adds a contemporary dimension to this conversation. GPTs, in their current state, demonstrate the foundational capabilities for agent development - from structured prompts facilitating diverse tasks to integration with various systems. As envisioned by Wooldridge, Jennings, and Mollick, the future points towards agents integrated with a myriad of systems capable of tasks like managing expense reports or optimizing financial decisions.

Yet, this promising future has its challenges. The road to developing fully autonomous intelligent agents is fraught with technical and ethical considerations. Issues like logical omniscience in agent reasoning, the relationship between intention and action, and managing conflicting intentions remain unresolved. Mollick raises concerns about the vulnerabilities and risks in an increasingly interconnected AI landscape.

The explosion in Agents will be fuelled, like throwing gasoline on a fire, by the opening of OpenAI's GPT store sometime in early 2024. Many online pundits will think "agents" are a new thing! But as this post shows, the ideas and vast body of AI research dates back to the mid-1990s and early 2000s; as exemplified by The Trading Agents Competition.

Intelligent Agents represent a transformative trend in AI for 2024 and beyond. Their development, grounded in a combination of theoretical and practical advancements, paves the way for a future where AI is not just a tool but a proactive, interactive, and intelligent entity. 

Weizenbaum's ELIZA: A Reflection on AI and Transference

Generated by DALL-E

Sometimes, the simplest creations leave the most profound impacts. This was true for Joseph Weizenbaum's ELIZA, a chatbot I became familiar with during my MSc studies in 1985. My first assignment was to code a version of ELIZA in Prolog, and it was surprisingly easy. Yet, the implications of this simple program were anything but.

ELIZA, created in the mid-1960s, was one of the earliest examples of what we now call a chatbot. Its most famous script, DOCTOR, simulated a Rogerian psychotherapist. This simplicity was deceptive; the program merely echoed user inputs in the form of questions, yet it evoked profound emotional responses from users.

(You can try out ELIZA for yourself here.)

When I was tasked with coding ELIZA in Prolog as a new AI MSc student, I was struck by the simplicity of the task. Prolog, with its natural language processing capabilities, seemed almost tailor-made for this assignment. The ease with which I could replicate aspects of ELIZA's functionality was both exhilarating and unnerving. It was a testament to both the power of declarative AI programming languages like Prolog and the ingenious design of ELIZA.

The real intrigue of ELIZA lies not in its technical complexity but in the psychological phenomenon recognised by Freud it inadvertently uncovered: transference. Users often attributed understanding, empathy, and even human-like concern to ELIZA despite knowing it was a mere program. This phenomenon highlighted the human tendency to anthropomorphise and seek connection, even in unlikely places.

Joseph Weizenbaum himself was startled by this phenomenon. As a technologist who understood the mechanical underpinnings of ELIZA, he was disturbed by the emotional attachment users developed with the program. This led him to become a vocal critic of unrestrained AI development, warning of the ethical and psychological implications.

My journey with ELIZA and Prolog was more than an academic exercise; it was a window into the complex relationship between humans and AI. It highlighted the ease with which we can create seemingly intelligent systems and the profound, often unintended, psychological impacts they can have. As we venture further into the age of ChatGPT, Weizenbaum's cautionary tale remains as relevant as ever.

In an era where AI is more advanced and pervasive, revisiting the lessons from ELIZA and Weizenbaum's reflections, as highlighted in articles like this recent one from The Guardian, is crucial. It reminds us that in our quest to advance AI, we must remain vigilant of the human element at the core of our interactions with machines. Weizenbaum's legacy, through Eliza, is not just a technological artefact but a cautionary tale about the depth of human interaction with machines and the ethical boundaries we must navigate as we move ahead in the realm of AI.

AI is (not) a bubble

 

Image generated by DALL-E

2023 has been an unprecedented year for Artificial Intelligence (AI). I know this because I have worked in the area since 1985 and have never seen AI get so much attention in the media. This is due to the release of ChatGPT and other generative AI applications based on Large Language Models capturing the public's attention like never before. Consequently, many pundits are nay-sayers, stating that AI is a bubble bound to burst, leaving fortunes in tatters and start-ups bankrupt. Undeniably, there is a small and finite market for apps that help students cheat on their essays or create the perfect dating site profile. However, AI is not a bubble. 

This blog post by Cory Doctorow What Kind of Bubble is AI? is typical, making the common error of conflating AI with Large Language Models (LLMs) like ChatGPT. ChatGPT is merely one type of AI which has a 70+ year research and development history. Your smartphone map app uses the A* algorithm to find your route from A to B. It was developed at the Stanford Research Institute (SRI) in 1968 (the same place that made Apple's Siri). Fuzzy logic manages the autofocus in your phone's camera. Case-based reasoning provides knowledge to the help desk operator when you call 0800, and there are countless other examples of different AI methods embedded in all aspects of modern society. Large Language Models are called by us AI people "Foundation Models" because they provide a foundation other AIs can use to provide a two-way multimodal conversational interface. Yes, they are expensive to build and train, but as their name suggests, you only need a few "Foundation" models to underly a multitude of applications. This is a genuine breakthrough that will have a lasting impact on the uptake of AI once essay-cheating apps fall out of the public's focus.

Cory Doctorow's blog post, for example, says that "Radiologists might value the AI's guess about whether an X-ray suggests a cancerous mass. But with AIs' tendency to "hallucinate" and confabulate, there's an increasing recognition that these AI judgments require a "human in the loop" to carefully review their judgments." This mistakenly assumes that medical image analysis uses the same techniques as LLMs like ChatGPT. They do not; they're a mature application of medical image analysis using rigorously tested machine-learning algorithms that do not "guess" or "hallucinate". A recently published paper, Redefining Radiology: A Review of Artificial Intelligence Integration in Medical Imaging, by Reabal Nadjjar (Diagnostics 2023, 13, 2760. https://doi.org/10.3390/diagnostics13172760), details the development of AI-assisted medical imaging. The article clearly shows that AI is now a fixture in medical image analysis and diagnosis, although there is always room for improvement.

AI is just coming of age. ChatGPT has focused a spotlight on AI, which is now mature enough and has the processing power in the cloud to succeed. Why wasn't A* a thing in the 1960s? Back then, there simply wasn't enough portable processing power (or GPS). 2024 is going to be the year of "agents." OpenAI's release of its GPT Builder and an app store for GPTs that can interact with a myriad of online resources and tools will focus attention on the notion of intelligent agents. Many ill-informed pundits will think this is a brand new invention, whereas once again, Intelligent Agents is a mature discipline within AI dating back to the mid-1990s. This review paper by Michael.Wooldridge and Nicholas Jennings: Intelligent Agents: Theory and Practice. Knowledge Engineering Review 10(2), 1995, would be an excellent place to realise that agents won't be a flash in the pan either.

Undeniably, there is a lot of hype around AI, but within the bubble is a solid core of mature technologies ready to be exploited by people with knowledge and imagination. 

Moore's Law visualised

 

Last week, a photo from my social media feeds perfectly illustrated Moore's Law. It shows a computer being manhandled into a local government building in 1957. A little Internet sleuthing revealed that it was an Elliot Series 405, revealing its full spec. These English business computers were 32-bit and had 8k of memory. That's not the entire computer; there were bulky peripherals, and a typical installation cost around £85,000. That's about $1,094,915 (USD) in today's value.

The computer below, shown against the same building, is a Raspberry Pi. Even a base model has 1GB of RAM, costing $100 or less. The photo is a beautiful illustration of Moore's Law, named after the late Gordon Moore, co-founder of Intel, who observed that the number of transistors in an integrated circuit doubles about every two years. Moore's Second Law also noted that the price fell.