Inventing Eliza: The First Chatbot’s Hidden Code

ELIZA is remembered as the world’s first AI star, a kindly therapist in chatbot form that gently probed users’ worries. Even its creator, Joseph Weizenbaum, was surprised by the warm reception given to his experiment in human-machine interaction. For some, it heralded an age of automated psychotherapy, while others believed the program demonstrated sentience, a fallacy soon known as the “ELIZA effect.” Based on published descriptions, ELIZA has been implemented on many different computers, but only recently has the actual source code been unearthed from MIT’s archives.

In Inventing ELIZA: How the First Chatbot Shaped the Future of AI, just published by MIT Press, a squad of researchers analyze the code and reveal a complex program capable of much more than faking psychiatry. In fact, it could assume several different personas. The authors have also created a faithful emulation of the therapist persona that you can try yourself after reading the book excerpt below.

When it debuted in the mid-1960s, the ELIZA software program transformed the way people thought about interacting with computers. As the first chatbot, ELIZA demonstrated how a calculation machine might engage in conversation, ushering in a host of social and technical questions that still resonate today. Now we don’t think twice about interacting with a machine in real time, conversing over text, or even speaking into the air to ask about the weather. In many ways, ELIZA shaped not only the way we think about interacting with computers but also how we think about them. It began to give a reality to the science fiction stories of how we expect computers to work.

This article is adapted from the new book “Inventing ELIZA: How the First Chatbot Shaped the Future of AI“ (MIT Press, 2026).

Although ELIZA was far from a faultless conversation partner, it astonished its users. The recent discovery and archaeology of the original ELIZA source code represents a significant intervention in the history of computing. By examining the actual implementation of ELIZA rather than relying on later reconstructions and reimplementations, we challenge taken-for-granted assumptions about this key software artifact.

For example, the source code reveals that ELIZA was not merely a simple pattern-matching chatbot but can be better understood as a sophisticated platform designed for multiple “personas,” or scripts, with a complex set of capabilities, including script editing and contextual memory. The script that most people conflate with the program ELIZA was actually called Doctor, which performed the role of a psychotherapist. Yet, like a modern chatbot prompted to behave with different personalities, ELIZA could take on many roles.

“This code and script…reveal underlying assumptions about language, therapy, and human-computer interaction that continue to influence modern AI development.”

This unearthed material transforms our understanding of early AI development by demonstrating that Joseph Weizenbaum’s technical innovations were far more advanced than previously documented. Moreover, the discrepancies between his published descriptions and the actual implementation help to show the gap between theoretical computational models and their material instantiations in computer source code, a tension that continues to shape digital culture today.

Although many technical innovations have emerged in the decades since ELIZA, examining the ELIZA/Doctor code offers a rare glimpse into one of the earliest formalized attempts to model human conversation. What makes ELIZA particularly fascinating is not only its historical significance but also what it reveals about Weizenbaum’s views on both computing and human interaction. This code and script do not merely showcase programming techniques of the 1960s; they reveal underlying assumptions about language, therapy, and human-computer interaction that continue to influence modern AI development. By examining this code, we can start to uncover the sophisticated linguistic and programming techniques that allowed a rudimentary pattern-matching system to create a convincing simulation of understanding. But before we can read the lines of code, let us offer an overview of the system.

How Did ELIZA Create Personas?

The architectural distinction between ELIZA and Doctor represents an important design decision in AI history. Think of ELIZA as a system for interaction and Doctor as one set of rules that Weizenbaum devised, among others. This separation, manifested in ELIZA’s system-script dichotomy, presaged numerous contemporary software patterns, from configuration-as-data to plug-in architectures and domain-specific languages.

Based on published journal articles, ELIZA was re-created on many platforms, such as the IBM PC. However, the actual source code sat untouched in the MIT archives for many years. VCF Museum at InfoAge

Without question, the historical context of 1960s computing fundamentally shaped ELIZA’s architecture as well. Decisions in computing that reflect material constraints create path dependencies and eventually become programming cultural norms. These constraints manifested in ELIZA’s single-pass processing, tape-based storage and stack-oriented implementation. Yet within these limitations, Weizenbaum crafted an elegant solution. These technical features, though invisible to the users, are crucial to creating the illusion of understanding that made ELIZA so compelling.

Weizenbaum explained many of ELIZA’s technical features in the 10-page paper published in the January 1966 edition of the journal Communications of the Association of Computing Machinery (CACM). But he chose to omit some essential details.

In that paper Weizenbaum published ELIZA’s best known dialogue, which begins,

This dialogue marked ELIZA’s public debut in 1966 as one of the examples produced by the Doctor script. By finding the source code for ELIZA and examining how it performs the Doctor script, we now better understand these two separate parts of a system and can explore the many other personas of ELIZA. In just some of the other scripts known to date, ELIZA was programmed to discuss math, poetry, color, paradoxes, synchronization, relativity, France, and elevators.

These scripts work like templates. They are structured data that direct the ELIZA system to “play” a particular task or role. By comparing archival and published ELIZA dialogues from interactions with a variety of scripts, including Doctor, we can understand more about bot personas and how they function, paying close attention to how a bot evokes social dynamics between system and interactor.

Ultimately, studying the dialogues and scripts demonstrates the crucial role that collaboration plays in these exchanges, as bot and user cocreate the sense of their interaction. To understand the full range of ELIZA’s capabilities and conversational possibilities, let’s take a look at the variety of scripts that were created for the ELIZA system.

What distinguishes each ELIZA script is both its subject matter and the linguistic and stylistic choices used to deliver that content. These choices are not neutral; they can be said to construct a particular persona with characteristics that emerge through the script’s language patterns, vocabulary, and conversational approach. In short, it matters not just what you say but how you say it too.

“The aim was less to create a functional automated therapist and more to find a suitably constrained role to match the limitations of the programming environment.”

For example, with the Doctor script Weizenbaum deliberately echoed the style of a Rogerian “talk” therapist. He chose this persona because the psychiatric mode is one of the few types of conversations in which one person can “assume the pose of knowing almost nothing of the real world. If, for example, one were to tell a psychiatrist ‘I went for a long boat ride’ and he responded, ‘Tell me about boats,’ one would not assume that he knew nothing about boats but that he had some purpose in so directing the subsequent conversation.”

The first users of ELIZA interacted with it via teletype terminals.VCF Museum at InfoAge

Thus, the most famous persona created for ELIZA was a technical convenience. As human-computer interaction expert Lucy Suchman explains, “The Doctor program exploited the maxim that shared premises can remain unspoken: that the less we say in conversation, the more what is said is assumed to be self-evident.” In creating the original ELIZA effect, less was more.

The aim was less to create a functional automated therapist and more to find a suitably constrained role to match the limitations of the programming environment. Then Weizenbaum composed the script to match the role by choosing specific words that evoked rhetorical tone and characterization, for example, LET’S DISCUSS FURTHER WHY YOU … WHAT DOES THAT SUGGEST TO YOU. In Doctor, the machine side of the conversation needs to appear like a good listener who cares about what the user has mentioned before, so it often includes the user’s text in its replies and keeps its responses open-ended. Because a real doctor would be inquisitive, the script contains lots ofWHAT andWHY questions. In other scripts and dialogues, the script keywords and assigned responses reveal the design decisions that help create different specific personas. This variation becomes increasingly apparent as we look at the wider range of ELIZA scripts.

What Were Some of ELIZA’s Alternate Personas?

Let’s start with a script called Neweng, short for New England. By the mid-1950s, scientists were already taking up Turing’s proposition for conversing with a computer as a tangible idea. In 1959, a “conversation machine” made by a small team at the University of Toronto Computation Centre could make small talk about the weather if preprompted with current data. Its script included a ranked series of time words, weather words, and emotion words, but the system had “a rather narrow outlook,” limited vocabulary, and no knowledge of syntax. According to its creators, “in spite of this crudity, the results in passable conversation are surprisingly good, which in a way is a commentary on the shallowness of ordinary conversation about the weather.”

This fragment of ELIZA’s source code shows how scripted responses were encoded, in this case to make ELIZA sound like a Rogerian therapist. MIT Libraries, Distinctive Collections

One of ELIZA’s test scripts found in the archive had a similar function. Neweng does not soothe, therapize, or instruct, but only makes small talk. It chats as if at a boring dinner party.

What can we learn from such a basic conversation in which it seems like nothing interesting is shared? Despite the bland chat, a persona emerges from the bot script in phrases like PLEASANTLY COOL and UP THERE and in locations like THE BEACHES ON LONG ISLAND SOUND. From such comments, we can begin to imagine a persona who has not only a certain vocabulary but also certain hobbies and vacation spots. Perhaps implicit assumptions of race and class emerge as well.

A chatty persona might take on many forms, depending on where and when the conversation occurs. This one seems reserved, perhaps fitting its setting in 1960s New England. The system reminds the user that Missouri is not a New England state, but what if this conversation took place in Missouri, Texas, or Mexico? The machine persona would sound different in its cadence, tone, and references. What would we come to understand about a chat persona from Fire Island, from Brooklyn, from Berlin? What would they sound like, and what topics would they discuss?

These differences in subject matter do matter. They imply personas with entirely different backgrounds and experience, giving users wholly different interactions and affective relations. In this way, the Neweng script demonstrates how even simple algorithms making contextual responses about geography could generate a convincing sense of personhood and place. Whereas Neweng could be said to have created a casual, conversational persona focused on light social exchange, other scripts pushed ELIZA into more structured and educational roles. These scripts demonstrate how the system could be adapted not just for friendly chatter but for teaching.

Edwin Taylor, at MIT’s Education Research Center, developed alternate scripts for ELIZA, testing its ability to act as a teacher.MIT Libraries, Distinctive Collections

Meet ELIZA the tutor, quite unlike ELIZA the therapist or the chatty neighbor. Intrvw, Canvec, FVP1, and Arithm are a set of ELIZA scripts created as teaching tools used in experiments by Edwin F. Taylor at MIT’s Education Research Center. These scripts run on later versions of ELIZA that incorporated an important technical innovation called conditional keyword matching.

Unlike the original ELIZA, which simply looked for keywords and generated responses based on their presence, these updated versions could track what had been discussed previously and branch into different conversational paths based on specific user answers. This development allowed ELIZA to simulate a kind of Socratic method, where a tutor guides learning through carefully sequenced questions that respond to student answers rather than simply presenting information.

These scripts construct the tutor persona through many subtle linguistic gestures that create characterization and rhetorical tone. This tone differs from that of Doctor, which asks open-ended questions and comes across as gentle and nonscientific. In the tutoring scripts, large blocks of informative text from the bot tend to dominate the conversation, and the tone is often more dry and unemotional in these explanations. The dialogues indicate structured scripts that include guidance to lead the student through narrow, Socratic learning paths.

In particular, the teaching scripts feature praise and critique. The dialogues for Intrvw, Canvec, and FVP1 are peppered with EXCELLENT, VERY GOOD, RIGHT YOU ARE, and CONGRATULATIONS. These create the sense of a supportive instructor cheering the student on. Such politeness has been taken up in contemporary bots like ChatGPT, which has been shown to perform better when people are polite back to it.

ELIZA could become a tutor more effectively as the system grew in its capabilities, another valuable reminder that ELIZA was not one program but a family of programs. After the publication of the 1966 CACM article, Weizenbaum continued to develop the systems for interaction and understanding. As an experiment, Weizenbaum wrote the Arithm script less as a tutor and more so to “to illustrate the power of the evaluator to which ELIZA has access.” It uses a friendly, plain language interface to let users do simple programming. The script can do calculations, assign variables to values, and perform operations on them. Math problems can be described in sentence form:

The updated 1967 version of the ELIZA system can accumulate facts and store additional information. In this later version of ELIZA, when the system does not recognize information, it asks follow-up questions to gain data. As Weizenbaum explains, “The present script is designed to reveal, as opposed to conceal, lack of understanding and misunderstanding. Notice, for example, that when the program is asked to compute the area of the ball, it doesn’t yet know that a ball is a sphere and that when the diameter of the ball needs to be computed the fact that a ball is an object has also not yet been established.” Unlike Doctor, which asks questions to keep the conversation going, Arithm is building its store of, if not knowledge, then data and logic statements.

Although the variety of scripts helps us to see how a range of personas could be constructed through script programming ELIZA, they represent only half of the conversational process. A script can establish a foundation for a persona, but that persona only emerges fully through interaction with users who engage with it, interpret it, and respond to it in ways that may confirm, challenge, or transform the script’s implicit character.