ELIZA: Difference between revisions
Jump to navigation
Jump to search
imported>(Oinkers42) added Category:1966 software using HotCat |
imported>BlaqWiedow →DOCTOR and Computational Therapy: Edited heading |
||
| Line 1: | Line 1: | ||
{{Short description| | {{Short description|Natural language processing computer program}} | ||
{{Other uses}} | |||
{{Redirect|DOCTOR||Doctor (disambiguation)}} | |||
{{Use mdy dates|date=April 2025}} | {{Use mdy dates|date=April 2025}} | ||
{{Infobox software | {{Infobox software | ||
| name = ELIZA | | name = ELIZA | ||
| Line 12: | Line 12: | ||
| author = [[Joseph Weizenbaum]] | | author = [[Joseph Weizenbaum]] | ||
| developer = [[MIT]] | | developer = [[MIT]] | ||
| released = 1966 | | released = {{Start year and age|1966}} | ||
| operating system = [[Compatible Time-Sharing System|CTSS]] | | operating system = [[Compatible Time-Sharing System|CTSS]] | ||
| platform = [[IBM 7094]] | | platform = [[IBM 7094]] | ||
| programming language = [[SLIP (programming language)|MAD-SLIP]] | | programming language = [[SLIP (programming language)|MAD-SLIP]] | ||
| genre = [[ | | genre = [[Chatbot]] | ||
| license = [[Public domain]] | | license = [[Public domain]] | ||
| website = {{URL|https://elizagen.org}} | | website = {{URL|https://elizagen.org}} | ||
}} | }} | ||
'''ELIZA''' is an early [[natural language processing]] [[computer program]] developed from 1964 to 1967<ref name="turing">{{Cite web |title = Alan Turing at 100 |url = http://news.harvard.edu/gazette/story/2012/09/alan-turing-at-100/ |website = Harvard Gazette |date = 13 September 2012 |access-date = 2016-02-22}}</ref> at [[MIT]] by [[Joseph Weizenbaum]].<ref name=":8">{{Cite book |last=Berry |first=David M. |title=Hello, I'm Eliza: Fünfzig Jahre Gespräche mit Computern |publisher=Projekt Verlag |year=2018 |isbn= | '''ELIZA''' is an early [[natural language processing]] [[computer program]] developed from 1964 to 1967<ref name="turing">{{Cite web |title = Alan Turing at 100 |url = http://news.harvard.edu/gazette/story/2012/09/alan-turing-at-100/ |website = Harvard Gazette |date = 13 September 2012 |access-date = 2016-02-22}}</ref> at [[MIT]] by [[Joseph Weizenbaum]].<ref name=":8">{{Cite book |last=Berry |first=David M. |title=Hello, I'm Eliza: Fünfzig Jahre Gespräche mit Computern |publisher=Projekt Verlag |year=2018 |isbn=978-3-89733-467-0 |language=de |trans-title=Hello, I'm Eliza: Fifty Years of Conversations with Computers |editor-last=Baranovska |editor-first=Marianna |edition=1st |location=Berlin |pages=53–70 |chapter=Weizenbaum, ELIZA and the End of Human Reason |editor-last2=Höltgen |editor-first2=Stefan}}</ref>{{sfn|Weizenbaum|1976}}{{pn|date=April 2025}} Created to explore communication between humans and machines, ELIZA simulated conversation by using a [[pattern matching]] and substitution [[methodology]] that gave users an illusion of [[natural-language understanding|understanding]] on the part of the program, but gave no response that could be considered really understanding what was being said by either party.<ref name=":2">{{Cite book |title=Paradigms of Artificial Intelligence Programming |last=Norvig |first=Peter |publisher=Morgan Kaufmann Publishers |year=1992 |isbn=978-1-55860-191-8 |location=New York |pages=151–154}}</ref><ref name=":6">{{Cite journal|last=Weizenbaum|first=Joseph|date=January 1966|title=ELIZA--A Computer Program for the Study of Natural Language Communication Between Man and Machine|url=https://dl.acm.org/doi/10.1145/365153.365168|journal=Communications of the ACM|volume=9|pages=36–45|doi=10.1145/365153.365168|s2cid=1896290}}</ref><ref name="Baranovska" /> Whereas the ELIZA program itself was written (originally)<ref>{{Cite web|title=ELIZAGEN - The Original ELIZA|url=https://sites.google.com/view/elizagen-org/the-original-eliza|access-date=2021-05-31 |website=sites.google.com |language=en-US|archive-date=August 13, 2021|archive-url=https://web.archive.org/web/20210813233541/https://sites.google.com/view/elizagen-org/the-original-eliza|url-status=dead}}</ref> in [[SLIP (programming language)|MAD-SLIP]], the pattern matching directives that contained most of its language capability were provided in separate "scripts", represented in a [[s-expression|Lisp-like expression]].<ref>{{Cite journal |last=Berry |first=David M. |date=2023-11-06 |title=The Limits of Computation: Joseph Weizenbaum and the ELIZA Chatbot |url=https://ojs.weizenbaum-institut.de/index.php/wjds/article/view/106 |journal=Weizenbaum Journal of the Digital Society |language=en |volume=3 |issue=3 |doi=10.34669/WI.WJDS/3.3.2 |issn=2748-5625}}</ref> The most famous script, DOCTOR, simulated a [[Rogerian psychotherapy|psychotherapist of the Rogerian school]] (in which the therapist often reflects back the patient's words to the patient),<ref name=":9">{{Cite journal |last=Dillon |first=Sarah |date=2020-01-02 |title=The Eliza effect and its dangers: from demystification to gender critique |url=https://doi.org/10.1080/14797585.2020.1754642 |journal=Journal for Cultural Research |volume=24 |issue=1 |pages=1–15 |doi=10.1080/14797585.2020.1754642 |s2cid=219465727 |issn=1479-7585}}</ref><ref name="rogers">{{Cite journal |title =The computational therapeutic: exploring Weizenbaum's ELIZA as a history of the present |journal=AI & Society |volume=34 |issue=4 |pages=803–812 |doi=10.1007/s00146-018-0825-9 |year=2019 |last1=Bassett |first1=Caroline |doi-access=free }}</ref><ref name="The Samantha Test">{{Cite magazine |title=The Samantha Test |magazine=[[The New Yorker]] |url=https://www.newyorker.com/culture/culture-desk/the-samantha-test/|access-date=2019-05-25 |archive-date=2020-07-31 |archive-url=https://web.archive.org/web/20200731160448/https://www.newyorker.com/culture/culture-desk/the-samantha-test/ |url-status=dead }}</ref> and used rules, dictated in the script, to respond with non-directional questions to user inputs. As such, ELIZA was one of the first [[chatbot]]s (originally "chatterbots") and one of the first programs capable of attempting the [[Turing test]].<ref>{{Cite book |last=Marino |first=Mark |url=https://www.proquest.com/openview/3c91805eb882d2a56d58aaa6f809fa50/ |title=Chatbot: The Gender and Race Performativity of Conversational Agents |publisher=University of California |year=2006}}</ref><ref>{{Cite journal |last1=Marino |first1=Mark C. |last2=Berry |first2=Dav id M. |date=2024-11-03 |title=Reading ELIZA: Critical Code Studies in Action |url=https://electronicbookreview.com/essay/reading-eliza-critical-code-studies-in-action/ |journal=Electronic Book Review |language=en-US}}</ref> | ||
Weizenbaum intended the program as a method to explore communication between humans and machines. He was surprised | Weizenbaum intended the program as a method to explore communication between humans and machines. He was surprised that some people, including his secretary, attributed human-like feelings to the computer program,{{Sfn|Weizenbaum|1976}}{{pn|date=April 2025}} a phenomenon that came to be called the [[ELIZA effect]]. Many academics believed that the program would be able to positively influence the lives of many people, particularly those with psychological issues, and that it could aid doctors working on such patients' treatment.{{Sfn|Weizenbaum|1976}}{{pn|date=April 2025}}<ref>{{cite journal |doi=10.1097/00005053-196602000-00005 |pmid=5936301 |title=A Computer Method of Psychotherapy |journal=The Journal of Nervous and Mental Disease |volume=142 |issue=2 |pages=148–52 |year=1966 |last1=Colby |first1=Kenneth Mark |last2=Watt |first2=James B. |last3=Gilbert |first3=John P. |s2cid=36947398 }}</ref> While ELIZA was capable of engaging in discourse, it could not converse with true understanding.<ref name=":3">{{cite journal |last1=Shah |first1=Huma |last2=Warwick |first2=Kevin |last3=Vallverdú |first3=Jordi |last4=Wu |first4=Defeng |year=2016 |title=Can machines talk? Comparison of Eliza with modern dialogue systems |url=https://curve.coventry.ac.uk/open/items/d4c5572d-3a8f-4ed1-b085-c88f8124fd74/1/Can+Machines+Talk_+CHB_Shah-Warwick_2016+(1).pdf |journal=Computers in Human Behavior |volume=58 |pages=278–95 |doi=10.1016/j.chb.2016.01.004 }}{{Dead link|date=July 2025 |bot=InternetArchiveBot |fix-attempted=yes }}</ref> However, many early users were convinced of ELIZA's intelligence and understanding, despite Weizenbaum's insistence to the contrary.<ref name="Baranovska">{{Cite book |title=Hello, I'm Eliza fünfzig Jahre Gespräche mit Computern |publisher=Bochum Freiburg projektverlag |year=2018 |isbn=978-3-89733-467-0 |editor-last=Baranovska |editor-first=Marianna |edition=1st |location=Bochum |oclc=1080933718 |editor-last2=Höltgen |editor-first2=Stefan}}</ref> | ||
The original ELIZA [[source code]] had been missing since its creation in the 1960s, as it was not common to publish articles that included source code at that time. However, more recently the MAD-SLIP source code was discovered in the MIT archives and published on various platforms, such as the [[Internet Archive]].<ref name=":7">{{Cite book |last1=Shrager |first1=Jeff |title=Hello, I'm Eliza: Fünfzig Jahre Gespräche mit Computern |last2=Berry |first2=David M. |last3=Hay |first3=Anthony |last4=Millican |first4=Peter |publisher=Projekt Verlag |year=2022 |editor-last=Baranovska |editor-first=Marianna |edition=2nd |location=Berlin |pages=247–248 |chapter=Finding ELIZA - Rediscovering Weizenbaum's Source Code, Comments and Faksimiles |editor-last2=Höltgen |editor-first2=Stefan}}</ref> The source code is of high historical interest since it demonstrates not only the specificity of programming languages and techniques at that time, but also the beginning of software layering and abstraction as a means of achieving sophisticated software programming. | The original ELIZA [[source code]] had been missing since its creation in the 1960s, as it was not common to publish articles that included source code at that time. However, more recently the MAD-SLIP source code was discovered in the MIT archives and published on various platforms, such as the [[Internet Archive]].<ref name=":7">{{Cite book |last1=Shrager |first1=Jeff |title=Hello, I'm Eliza: Fünfzig Jahre Gespräche mit Computern |last2=Berry |first2=David M. |last3=Hay |first3=Anthony |last4=Millican |first4=Peter |publisher=Projekt Verlag |year=2022 |editor-last=Baranovska |editor-first=Marianna |edition=2nd |location=Berlin |pages=247–248 |chapter=Finding ELIZA - Rediscovering Weizenbaum's Source Code, Comments and Faksimiles |editor-last2=Höltgen |editor-first2=Stefan}}</ref> The source code is of high historical interest since it demonstrates not only the specificity of programming languages and techniques at that time, but also the beginning of software layering and abstraction as a means of achieving sophisticated software programming. | ||
| Line 29: | Line 29: | ||
==Overview== | ==Overview== | ||
[[File:Video Game Museum in Berlin (44129332940).jpg|thumb|A conversation between a human and ELIZA's DOCTOR script]] | [[File:Video Game Museum in Berlin (44129332940).jpg|thumb|A conversation between a human and ELIZA's DOCTOR script]] | ||
[[Joseph Weizenbaum]]'s ELIZA, running the DOCTOR script, created a conversational interaction somewhat similar to what might take place in the office of "a [non-directive] psychotherapist in an initial psychiatric interview"{{sfn|Weizenbaum|1976|p=188}} and to "demonstrate that the communication between man and machine was superficial".<ref>{{cite journal |doi=10.1016/S0747-5632(01)00004-8 |title=From Eliza to Internet: A brief history of computerized assessment |journal=Computers in Human Behavior |volume=17 |issue=3 |pages=295–314 |year=2001 |last1=Epstein |first1=J. |last2=Klinkenberg |first2=W. D. }}</ref> While ELIZA is best known for acting in the manner of a psychotherapist, the speech patterns are due to the data and instructions supplied by the DOCTOR script.<ref name=":4">{{cite journal |doi=10.1162/leon.2007.40.1.31 |jstor=20206337 |title=ELIZA REDUX: A Mutable Iteration |journal=Leonardo |volume=40 |issue=1 |pages=31–6 |year=2007 |last1=Wortzel |first1=Adrianne |s2cid=57565169 }}</ref> ELIZA itself examined the text for keywords, applied values to said keywords, and transformed the input into an output; the script that ELIZA ran determined the keywords, set the values of keywords, and set the rules of transformation for the output.<ref name=":1">{{cite journal |doi=10.1145/365153.365168 |title=ELIZA—a computer program for the study of natural language communication between man and machine |journal=Communications of the ACM |volume=9 |pages=36–45 |year=1966 |last1=Weizenbaum |first1=Joseph |s2cid=1896290 |doi-access=free }}</ref> Weizenbaum chose to make the DOCTOR script in the context of psychotherapy to "sidestep the problem of giving the program a data base of real-world knowledge",{{sfn|Weizenbaum|1976}}{{pn|date=April 2025}} allowing it to reflect back the patient's statements to carry the conversation forward.{{sfn|Weizenbaum|1976}}{{pn|date=April 2025}} The result was a somewhat intelligent-seeming response that reportedly deceived some early users of the program.<ref name="Wardip">{{cite book |last=Wardrip-Fruin |first=Noah |oclc=827013290 |page=33 |title=Expressive Processing: Digital Fictions, Computer Games, and Software Studies |date=2009 |publisher=MIT Press |isbn= | |||
[[Joseph Weizenbaum]]'s ELIZA, running the DOCTOR script, created a conversational interaction somewhat similar to what might take place in the office of "a [non-directive] psychotherapist in an initial psychiatric interview"{{sfn|Weizenbaum|1976|p=188}} and to "demonstrate that the communication between man and machine was superficial".<ref>{{cite journal |doi=10.1016/S0747-5632(01)00004-8 |title=From Eliza to Internet: A brief history of computerized assessment |journal=Computers in Human Behavior |volume=17 |issue=3 |pages=295–314 |year=2001 |last1=Epstein |first1=J. |last2=Klinkenberg |first2=W. D. }}</ref> While ELIZA is best known for acting in the manner of a psychotherapist, the speech patterns are due to the data and instructions supplied by the DOCTOR script.<ref name=":4">{{cite journal |doi=10.1162/leon.2007.40.1.31 |jstor=20206337 |title=ELIZA REDUX: A Mutable Iteration |journal=Leonardo |volume=40 |issue=1 |pages=31–6 |year=2007 |last1=Wortzel |first1=Adrianne |s2cid=57565169 }}</ref> ELIZA itself examined the text for keywords, applied values to said keywords, and transformed the input into an output; the script that ELIZA ran determined the keywords, set the values of keywords, and set the rules of transformation for the output.<ref name=":1">{{cite journal |doi=10.1145/365153.365168 |title=ELIZA—a computer program for the study of natural language communication between man and machine |journal=Communications of the ACM |volume=9 |pages=36–45 |year=1966 |last1=Weizenbaum |first1=Joseph |s2cid=1896290 |doi-access=free }}</ref> Weizenbaum chose to make the DOCTOR script in the context of psychotherapy to "sidestep the problem of giving the program a data base of real-world knowledge",{{sfn|Weizenbaum|1976}}{{pn|date=April 2025}} allowing it to reflect back the patient's statements to carry the conversation forward.{{sfn|Weizenbaum|1976}}{{pn|date=April 2025}} The result was a somewhat intelligent-seeming response that reportedly deceived some early users of the program.<ref name="Wardip">{{cite book |last=Wardrip-Fruin |first=Noah |oclc=827013290 |page=33 |title=Expressive Processing: Digital Fictions, Computer Games, and Software Studies |date=2009 |publisher=MIT Press |isbn=978-0-262-01343-7 |location=Cambridge, Massachusetts}}</ref> | |||
Weizenbaum named his program ELIZA after [[Eliza Doolittle]], a working-class character in [[George Bernard Shaw]]'s ''[[Pygmalion (play)|Pygmalion]]'' (also appearing in the musical ''[[My Fair Lady]]'', which was based on the play and was hugely popular at the time). According to Weizenbaum, ELIZA's ability to be "incrementally improved" by various users made it similar to Eliza Doolittle,<ref name=":1"/> since Eliza Doolittle was taught to speak with an [[upper-class]] [[Accent (sociolinguistics)|accent]] in Shaw's play.<ref name=":9" /><ref name="weizenbaumobit">{{Citation |last=Markoff |first=John |title=Joseph Weizenbaum, Famed Programmer, Is Dead at 85 |date=2008-03-13 |url=https://www.nytimes.com/2008/03/13/world/europe/13weizenbaum.html |author-link=John Markoff |work=[[The New York Times]] |access-date=2009-01-07}}.</ref> However, unlike the human character in Shaw's play, ELIZA is incapable of learning new patterns of speech or new words through interaction alone. Edits must be made directly to ELIZA's active script in order to change the manner by which the program operates. | Weizenbaum named his program ELIZA after [[Eliza Doolittle]], a working-class character in [[George Bernard Shaw]]'s ''[[Pygmalion (play)|Pygmalion]]'' (also appearing in the musical ''[[My Fair Lady]]'', which was based on the play and was hugely popular at the time). According to Weizenbaum, ELIZA's ability to be "incrementally improved" by various users made it similar to Eliza Doolittle,<ref name=":1"/> since Eliza Doolittle was taught to speak with an [[upper-class]] [[Accent (sociolinguistics)|accent]] in Shaw's play.<ref name=":9" /><ref name="weizenbaumobit">{{Citation |last=Markoff |first=John |title=Joseph Weizenbaum, Famed Programmer, Is Dead at 85 |date=2008-03-13 |url=https://www.nytimes.com/2008/03/13/world/europe/13weizenbaum.html |author-link=John Markoff |work=[[The New York Times]] |access-date=2009-01-07}}.</ref> However, unlike the human character in Shaw's play, ELIZA is incapable of learning new patterns of speech or new words through interaction alone. Edits must be made directly to ELIZA's active script in order to change the manner by which the program operates. | ||
| Line 35: | Line 36: | ||
Weizenbaum first implemented ELIZA in his own [[SLIP (programming language)|SLIP]] list-processing language, where, depending upon the initial entries by the user, the illusion of human intelligence could appear, or be dispelled through several interchanges.<ref name=":8" /> Some of ELIZA's responses were so convincing that Weizenbaum and several others have anecdotes of users becoming emotionally attached to the program, occasionally forgetting that they were conversing with a computer.{{sfn|Weizenbaum|1976}}{{pn|date=April 2025}} Weizenbaum's own secretary reportedly asked Weizenbaum to leave the room so that she and ELIZA could have a real conversation. Weizenbaum was surprised by this, later writing: "I had not realized ... that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people."{{sfn|Weizenbaum|1976|p=7}} | Weizenbaum first implemented ELIZA in his own [[SLIP (programming language)|SLIP]] list-processing language, where, depending upon the initial entries by the user, the illusion of human intelligence could appear, or be dispelled through several interchanges.<ref name=":8" /> Some of ELIZA's responses were so convincing that Weizenbaum and several others have anecdotes of users becoming emotionally attached to the program, occasionally forgetting that they were conversing with a computer.{{sfn|Weizenbaum|1976}}{{pn|date=April 2025}} Weizenbaum's own secretary reportedly asked Weizenbaum to leave the room so that she and ELIZA could have a real conversation. Weizenbaum was surprised by this, later writing: "I had not realized ... that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people."{{sfn|Weizenbaum|1976|p=7}} | ||
In 1966, interactive computing (via a teletype) was new. It was 11 years before the personal computer became familiar to the general public, and three decades before most people encountered attempts at [[natural language processing]] in Internet services like [[Ask.com]] or PC help systems such as Microsoft Office [[Office Assistant|Clippit]].<ref>{{Cite web |last=Meyer |first=Robinson |date=2015-06-23 |title=Even Early Focus Groups Hated Clippy |url=https://www.theatlantic.com/technology/archive/2015/06/clippy-the-microsoft-office-assistant-is-the-patriarchys-fault/396653/ |access-date=2023-11-07 |website=The Atlantic |language=en}}</ref> Although those programs included years of research and work, ELIZA remains a milestone because it was the first time a programmer had attempted such a human-machine interaction with the goal of creating the illusion (however brief) of human–''human'' interaction.{{ | In 1966, interactive computing (via a teletype) was new. It was 11 years before the personal computer became familiar to the general public, and three decades before most people encountered attempts at [[natural language processing]] in Internet services like [[Ask.com]] or PC help systems such as Microsoft Office [[Office Assistant|Clippit]].<ref>{{Cite web |last=Meyer |first=Robinson |date=2015-06-23 |title=Even Early Focus Groups Hated Clippy |url=https://www.theatlantic.com/technology/archive/2015/06/clippy-the-microsoft-office-assistant-is-the-patriarchys-fault/396653/ |access-date=2023-11-07 |website=The Atlantic |language=en}}</ref> Although those programs included years of research and work, ELIZA remains a milestone because it was the first time a programmer had attempted such a human-machine interaction with the goal of creating the illusion (however brief) of human–''human'' interaction.<ref>{{Cite journal |last=Weizenbaum |first=Joseph |title=ELIZA — A Computer Program For the Study of Natural Language Communication Between Man and Machine |journal=Communications of the ACM |volume=9 |issue=1 |pages=36–45 |year=1966 |doi=10.1145/365153.365168}}</ref> | ||
At the [[International Conference on Computer Communications|ICCC 1972]], ELIZA was brought together with another early artificial-intelligence program named [[PARRY]] for a computer-only conversation. While ELIZA was built to speak as a doctor, PARRY was intended to simulate a patient with [[schizophrenia]].<ref name="PerryElizaAtlantic">{{cite magazine |last1=Megan |first1=Garber |title=When PARRY Met ELIZA: A Ridiculous Chatbot Conversation From 1972 |url=https://www.theatlantic.com/technology/archive/2014/06/when-parry-met-eliza-a-ridiculous-chatbot-conversation-from-1972/372428/ |magazine=The Atlantic |access-date=19 January 2017 |archive-url=https://web.archive.org/web/20170118165304/http://www.theatlantic.com/technology/archive/2014/06/when-parry-met-eliza-a-ridiculous-chatbot-conversation-from-1972/372428/ |archive-date=2017-01-18 |url-status=live |date=Jun 9, 2014}}</ref> | At the [[International Conference on Computer Communications|ICCC 1972]], ELIZA was brought together with another early artificial-intelligence program named [[PARRY]] for a computer-only conversation. While ELIZA was built to speak as a doctor, PARRY was intended to simulate a patient with [[schizophrenia]].<ref name="PerryElizaAtlantic">{{cite magazine |last1=Megan |first1=Garber |title=When PARRY Met ELIZA: A Ridiculous Chatbot Conversation From 1972 |url=https://www.theatlantic.com/technology/archive/2014/06/when-parry-met-eliza-a-ridiculous-chatbot-conversation-from-1972/372428/ |magazine=The Atlantic |access-date=19 January 2017 |archive-url=https://web.archive.org/web/20170118165304/http://www.theatlantic.com/technology/archive/2014/06/when-parry-met-eliza-a-ridiculous-chatbot-conversation-from-1972/372428/ |archive-date=2017-01-18 |url-status=live |date=Jun 9, 2014}}</ref> | ||
==Design and implementation== | ==Design and implementation== | ||
Weizenbaum originally wrote ELIZA in MAD-SLIP for [[Compatible Time-Sharing System|CTSS]] on an [[IBM 7094]] as a program to make natural-language conversation possible with a computer.<ref>{{cite web |url=https://multicians.org/thvv/compatible-time-sharing-system.pdf |title=Compatible Time-Sharing System (1961-1973): Fiftieth Anniversary Commemorative Overview |editor-last1=Walden |editor-first1=David |editor-last2=Van Vleck |editor-first2=Tom |editor2-link=Tom Van Vleck |date=2011 |publisher=IEEE Computer Society |access-date=February 20, 2022 |quote=Joe Wiezenbaum's most famous CTSS project was ELIZA}}</ref> To accomplish this, Weizenbaum identified five "fundamental technical problems" for ELIZA to overcome: the identification of key words, the discovery of a minimal context, the choice of appropriate transformations, the generation of responses in the absence of key words, and the provision of an editing capability for ELIZA scripts.<ref name=":1" /> Weizenbaum solved these problems and made ELIZA such that it had no built-in contextual framework or universe of discourse.<ref name=":4" /> However, this required ELIZA to have a script of instructions on how to respond to inputs from users.<ref name="Baranovska" /> | Weizenbaum originally wrote ELIZA in MAD-SLIP for [[Compatible Time-Sharing System|CTSS]] on an [[IBM 7094]] as a program to make natural-language conversation possible with a computer.<ref>{{cite web |url=https://multicians.org/thvv/compatible-time-sharing-system.pdf |title=Compatible Time-Sharing System (1961-1973): Fiftieth Anniversary Commemorative Overview |editor-last1=Walden |editor-first1=David |editor-last2=Van Vleck |editor-first2=Tom |editor2-link=Tom Van Vleck |date=2011 |publisher=IEEE Computer Society |access-date=February 20, 2022 |quote=Joe Wiezenbaum's most famous CTSS project was ELIZA}}</ref> To accomplish this, Weizenbaum identified five "fundamental technical problems" for ELIZA to overcome: the identification of key words, the discovery of a minimal context, the choice of appropriate transformations, the generation of responses in the absence of key words, and the provision of an editing capability for ELIZA scripts.<ref name=":1" /> Weizenbaum solved these problems and made ELIZA such that it had no built-in contextual framework or universe of discourse.<ref name=":4" /> However, this required ELIZA to have a script of instructions on how to respond to inputs from users.<ref name="Baranovska" /> | ||
| Line 49: | Line 49: | ||
The decomposition rule then designates a particular reassembly rule, or set of reassembly rules, to follow when reconstructing the sentence.<ref name=":6" /> The reassembly rule takes the fragments of the input that the decomposition rule had created, rearranges them, and adds in programmed words to create a response. Using Weizenbaum's example previously stated, such a reassembly rule would take the fragments and apply them to the phrase "What makes you think I am (4)", which would result in "What makes you think I am very helpful?". This example is rather simple, since depending upon the disassembly rule, the output could be significantly more complex and use more of the input from the user. However, from this reassembly, ELIZA then sends the constructed sentence to the user in the form of text on the screen.<ref name=":1" /> | The decomposition rule then designates a particular reassembly rule, or set of reassembly rules, to follow when reconstructing the sentence.<ref name=":6" /> The reassembly rule takes the fragments of the input that the decomposition rule had created, rearranges them, and adds in programmed words to create a response. Using Weizenbaum's example previously stated, such a reassembly rule would take the fragments and apply them to the phrase "What makes you think I am (4)", which would result in "What makes you think I am very helpful?". This example is rather simple, since depending upon the disassembly rule, the output could be significantly more complex and use more of the input from the user. However, from this reassembly, ELIZA then sends the constructed sentence to the user in the form of text on the screen.<ref name=":1" /> | ||
These steps represent the bulk of the procedures that ELIZA follows in order to create a response from a typical input, though there are several specialized situations that ELIZA/DOCTOR can respond to. One Weizenbaum specifically wrote about was when there is no keyword. One solution was to have ELIZA respond with a remark that lacked content, such as "I see" or "Please go on".<ref name=":1" /> The second method was to use a "MEMORY" structure, which recorded prior recent inputs, and would use these inputs to create a response referencing a part of the earlier conversation when encountered with no keywords.<ref name=":5">{{Cite book |title=Expressive Processing: Digital Fictions, Computer Games, and Software Studies |last=Wardip-Fruin |first=Noah |publisher=The MIT Press |year=2014 |isbn= | These steps represent the bulk of the procedures that ELIZA follows in order to create a response from a typical input, though there are several specialized situations that ELIZA/DOCTOR can respond to. One Weizenbaum specifically wrote about was when there is no keyword. One solution was to have ELIZA respond with a remark that lacked content, such as "I see" or "Please go on".<ref name=":1" /> The second method was to use a "MEMORY" structure, which recorded prior recent inputs, and would use these inputs to create a response referencing a part of the earlier conversation when encountered with no keywords.<ref name=":5">{{Cite book |title=Expressive Processing: Digital Fictions, Computer Games, and Software Studies |last=Wardip-Fruin |first=Noah |publisher=The MIT Press |year=2014 |isbn=978-0-262-01343-7 |location=Cambridge |page=33 |via=eBook Collection (EBSCOhost)}}</ref> This was possible due to Slip's ability to tag words for other usage, which simultaneously allowed ELIZA to examine, store, and repurpose words for usage in outputs.<ref name=":1" /> | ||
While these functions were all framed in ELIZA's programming, the exact manner by which the program dismantled, examined, and reassembled inputs is determined by the operating script. The script is not static and can be edited, or a new one created, as is necessary for the operation in the context needed. This would allow the program to be applied in multiple situations, including the well-known DOCTOR script, which simulates a Rogerian psychotherapist.<ref name=":7" /> | While these functions were all framed in ELIZA's programming, the exact manner by which the program dismantled, examined, and reassembled inputs is determined by the operating script. The script is not static and can be edited, or a new one created, as is necessary for the operation in the context needed. This would allow the program to be applied in multiple situations, including the well-known DOCTOR script, which simulates a Rogerian psychotherapist.<ref name=":7" /> | ||
| Line 57: | Line 57: | ||
In 2021, Jeff Shrager searched MIT's Weizenbaum archives, along with [[Massachusetts Institute of Technology|MIT]] archivist Myles Crowley, and found files labeled Computer Conversations. These included the complete source code listing of ELIZA in MAD-SLIP, with the DOCTOR script attached. The Weizenbaum estate gave permission to open-source this code under a [[Creative Commons]] CC0 [[public domain]] license. The code and other information can be found on the ELIZAGEN site.<ref name="elizagen" /> The 1965 source code has been dated as part of a software archaeology project which brings together researchers from [[University of Southern California|USC]], [[University of Sussex]], [[University of Oxford|Oxford]], and [[Stanford University]], who have worked together to unravel the complicated history of ELIZA.<ref>{{Cite journal |last=Marino |first=Dav id M. Berry Mark C. |date=2024-11-03 |title=Reading ELIZA: Critical Code Studies in Action |url=https://electronicbookreview.com/essay/reading-eliza-critical-code-studies-in-action/ |journal=Electronic Book Review |language=en-US}}</ref> | In 2021, Jeff Shrager searched MIT's Weizenbaum archives, along with [[Massachusetts Institute of Technology|MIT]] archivist Myles Crowley, and found files labeled Computer Conversations. These included the complete source code listing of ELIZA in MAD-SLIP, with the DOCTOR script attached. The Weizenbaum estate gave permission to open-source this code under a [[Creative Commons]] CC0 [[public domain]] license. The code and other information can be found on the ELIZAGEN site.<ref name="elizagen" /> The 1965 source code has been dated as part of a software archaeology project which brings together researchers from [[University of Southern California|USC]], [[University of Sussex]], [[University of Oxford|Oxford]], and [[Stanford University]], who have worked together to unravel the complicated history of ELIZA.<ref>{{Cite journal |last=Marino |first=Dav id M. Berry Mark C. |date=2024-11-03 |title=Reading ELIZA: Critical Code Studies in Action |url=https://electronicbookreview.com/essay/reading-eliza-critical-code-studies-in-action/ |journal=Electronic Book Review |language=en-US}}</ref> | ||
In December 2024, Rupert Lane, with the assistance of several other engineers who had been studying the original MAD-SLIP ELIZA, brought up the original ELIZA and demonstrated that the implementation of ELIZA based on the discovered code can reproduce almost exactly the published conversations with ELIZA from Weizenbaum's 1966 paper. This original ELIZA was reconstructed using the vast majority of the 1965 version of the source code: approximately 96% of the functions.<ref>{{Cite web |last=Berry |first=David M. |date=2025 |title=Digital Ruins and Critical Code Studies: Towards an Ethics of Historical Software Reconstruction |url=https://stunlaw.blogspot.com/2025/01/digital-ruins-and-critical-code-studies.html |access-date=2025-01-26 |website=Stunlaw}}</ref> This was run on a version of the original MIT [[Compatible Time Sharing System|CTSS]] running on a [[IBM 7090#IBM 7094|7094]] emulator, both of the latter due to David Pitts.<ref name="ELIZA Reanimated">{{cite web|title=ELIZA Reanimated|url=https://sites.google.com/view/elizagen-org/blog/eliza-reanimated|website=elizagen.org}}</ref><ref>{{cite web | url = https://www.livescience.com/technology/eliza-the-worlds-1st-chatbot-was-just-resurrected-from-60-year-old-computer-code | title = 'ELIZA,' the world's 1st chatbot, was just resurrected from 60-year-old computer code | first = Kristina | last = Killgrove | date = January 18, 2025 | accessdate = January 18, 2025 | work = [[Live Science]] }}</ref> | In December 2024, Rupert Lane, with the assistance of several other engineers who had been studying the original MAD-SLIP ELIZA, brought up the original ELIZA and demonstrated that the implementation of ELIZA based on the discovered code can reproduce almost exactly the published conversations with ELIZA from Weizenbaum's 1966 paper. This original ELIZA was reconstructed using the vast majority of the 1965 version of the source code: approximately 96% of the functions.<ref>{{Cite web |last=Berry |first=David M. |date=2025 |title=Digital Ruins and Critical Code Studies: Towards an Ethics of Historical Software Reconstruction |url=https://stunlaw.blogspot.com/2025/01/digital-ruins-and-critical-code-studies.html |access-date=2025-01-26 |website=Stunlaw}}</ref> This was run on a version of the original MIT [[Compatible Time-Sharing System|CTSS]] running on a [[IBM 7090#IBM 7094|7094]] emulator, both of the latter due to David Pitts.<ref name="ELIZA Reanimated">{{cite web|title=ELIZA Reanimated|url=https://sites.google.com/view/elizagen-org/blog/eliza-reanimated|website=elizagen.org}}</ref><ref>{{cite web | url = https://www.livescience.com/technology/eliza-the-worlds-1st-chatbot-was-just-resurrected-from-60-year-old-computer-code | title = 'ELIZA,' the world's 1st chatbot, was just resurrected from 60-year-old computer code | first = Kristina | last = Killgrove | date = January 18, 2025 | accessdate = January 18, 2025 | work = [[Live Science]] }}</ref> | ||
Another version of Eliza popular among software engineers is the version that comes with the default release of [[GNU Emacs]], and which can be accessed by typing <code>[[Meta key|M]]-x doctor</code> from most modern [[Emacs]] implementations. | Another version of Eliza popular among software engineers is the version that comes with the default release of [[GNU Emacs]], and which can be accessed by typing <code>[[Meta key|M]]-x doctor</code> from most modern [[Emacs]] implementations. | ||
=== Pseudocode === | === Pseudocode === | ||
From Figure 15.5, Chapter 15 of Speech and Language Processing (third edition).<ref>{{cite web|url=https://web.stanford.edu/~jurafsky/slp3/15.pdf|access-date=6 April 2023|website=stanford.edu|title=Chatbots & Dialogue Systems}}</ref> | From Figure 15.5, Chapter 15 of ''Speech and Language Processing'' (third edition).<ref>{{cite web|url=https://web.stanford.edu/~jurafsky/slp3/15.pdf|access-date=6 April 2023|website=stanford.edu|title=Chatbots & Dialogue Systems}}</ref> | ||
function ELIZA GENERATOR(user ''sentence'') returns ''response'' | function ELIZA GENERATOR(user ''sentence'') returns ''response'' | ||
Let ''w'' be the word in ''sentence'' that has the highest keyword rank | Let ''w'' be the word in ''sentence'' that has the highest keyword rank | ||
| Line 88: | Line 88: | ||
ELIZA won a 2021 Legacy [[Peabody Award]]. A 2023 [[preprint]] reported that ELIZA beat [[OpenAI]]'s [[GPT-3.5]], the model used by [[ChatGPT]] at the time, in a [[Turing test]] study. However, it did not outperform [[GPT-4]] or real humans.<ref>{{Cite web |last=Edwards |first=Benj |date=2023-12-01 |title=1960s chatbot ELIZA beat OpenAI's GPT-3.5 in a recent Turing test study |url=https://arstechnica.com/information-technology/2023/12/real-humans-appeared-human-63-of-the-time-in-recent-turing-test-ai-study/ |access-date=2023-12-03 |website=Ars Technica |language=en-us}}</ref><ref>{{Citation |last1=Jones |first1=Cameron R. |title=Does GPT-4 pass the Turing test? |date=2024-04-20 |arxiv=2310.20216 |last2=Bergen |first2=Benjamin K.}}</ref> | ELIZA won a 2021 Legacy [[Peabody Award]]. A 2023 [[preprint]] reported that ELIZA beat [[OpenAI]]'s [[GPT-3.5]], the model used by [[ChatGPT]] at the time, in a [[Turing test]] study. However, it did not outperform [[GPT-4]] or real humans.<ref>{{Cite web |last=Edwards |first=Benj |date=2023-12-01 |title=1960s chatbot ELIZA beat OpenAI's GPT-3.5 in a recent Turing test study |url=https://arstechnica.com/information-technology/2023/12/real-humans-appeared-human-63-of-the-time-in-recent-turing-test-ai-study/ |access-date=2023-12-03 |website=Ars Technica |language=en-us}}</ref><ref>{{Citation |last1=Jones |first1=Cameron R. |title=Does GPT-4 pass the Turing test? |date=2024-04-20 |arxiv=2310.20216 |last2=Bergen |first2=Benjamin K.}}</ref> | ||
=== Historical purpose and interpretation === | |||
Although ELIZA is often described as an early chatbot, [[Joseph Weizenbaum]] presented it as a program for investigating natural language communication between machines and humans. In Weizenbaum’s 1966 article, he described ELIZA as a system that applied a pattern-matching mechanism along with interchanging scripts, where the most famous one was DOCTOR.<ref>{{Cite journal |last=Weizenbaum |first=Joseph |date=January 1966 |title=ELIZA—a computer program for the study of natural language communication between man and machine |url=https://doi.org/10.1145/365153.365168 |journal=Communications of the ACM |volume=9 |issue=1 |pages=36–45 |doi=10.1145/365153.365168 |issn=0001-0782}}</ref> It produced responses that resembled those of [[psychotherapists]]. Instead of understanding language semantically, ELIZA identified keywords and transformed the input of users into brand new prompts. As a result, scholars later have noted that this particular structure made ELIZA important in the history of conversational programs and discussions on the limitations of machine understanding. | |||
Recent historical discourse echoes this idea that Weizenbaum did not primarily intend to create ELIZA as a chatbot, but as a unique platform for investigating how humans converse with machines and the important cognitive processes of interpretation and misinterpretation.<ref>{{Cite web |title=ELIZA Reinterpreted: The world’s first chatbot was not intended as a chatbot at all |url=https://arxiv.org/html/2406.17650v2 |access-date=2026-05-28 |website=arxiv.org}}</ref>ELIZA’s later reputation as the first chatbot was shaped by the timing of its creation and circulation beyond its original research context. Another reason was the subsequent loss of access to the original source code for more than fifty years, which led to more room for interpretation. As a result, ELIZA appeared in several developments in the history of artificial intelligence, including [[natural language processing]] and other systems and programming languages. | |||
In 2021, the original source code for Weizenbaum’s ELIZA was publicized through the [[Internet Archive]].<ref>{{Cite book |last=Joseph Weizenbaum |url=http://archive.org/details/eliza_1966_mad_slip_src |title=Original ELIZA source code in MAD-SLIP |date=2021-05-28}}</ref> Researchers were able to study the recovered materials containing the ELIZA program and the DOCTOR script more directly as a primary historical artifact. Consequently, scholars attempted to recreate how the program would operate in its original computational environment and MIT implementation.<ref>{{Cite web |title=ELIZAGEN - Original ELIZA |url=https://sites.google.com/view/elizagen-org/original-eliza |access-date=2026-05-28 |website=sites.google.com |language=en-US}}</ref> The recovered source code created a distinction between ELIZA’s real technical architecture and its later reputation in chatbot development. Recent reconstruction work from the recovered source code has allowed modern-day researchers to understand ELIZA’s precise technical operation and compare it with its later reputation and reassess its historical role in artificial intelligence and [[chatbot]] development. | |||
=== DOCTOR and computational therapy === | |||
The DOCTOR script is the best-known example of ELIZA as it simulates the mode of [[Person-centered therapy|Rogerian psychotherapy]]. It functions by reinterpreting the user’s own input of words in the form of questions or prompts, which allows it to proceed with a conversation while making relatively few claims about the person’s situation. | |||
The receptions of ELIZA impacted Weizenbaum’s later critique of artificial intelligence and the authority of computation. In ''[[Computer Power and Human Reason]]'', he openly opposed the view that human thoughts can be completely reduced to computation power, and also questioned the emerging tendency to view computers as suitable replacements for human cognitive judgment in both social and ethical domains. Scholar [[Caroline Bassett]] argued that ELIZA’s importance lied in its role as an early prototype of computational therapy.<ref>Bassett, C. The computational therapeutic: exploring Weizenbaum’s ELIZA as a history of the present. ''AI & Soc'' 34, 803–812 (2019). <nowiki>https://doi.org/10.1007/s00146-018-0825-9</nowiki></ref> The DOCTOR script with a relatively simple conversational program was able to create a setting with users that imitated human care, understanding, and expertise. Other scholars like [[Noah Wardrip-Fruin]] have also treated ELIZA as a significant example in software studies where the user’s experience relied on the interaction between the underlying code, the script, and the interpretive expectations in the process.<ref>Wardrip-Fruin, Noah. ''Expressive Processing: Digital Fictions, Computer Games, and Software Studies''. Cambridge, MA: MIT Press, 2009.</ref> As a result, ELIZA became important not only as an early conversational program, but also as an example where later scholars have examined [[human-machine interaction]], physiological and behavioral influence, and how they perceived the intelligence of computer systems. | |||
=== Eliza Effect === | === Eliza Effect === | ||
| Line 100: | Line 112: | ||
===Bibliography=== | ===Bibliography=== | ||
* {{Citation |last=Norvig |first=Peter |title=ELIZA: Paradigms of Artificial Intelligence Programming |place=San Francisco |publisher=Morgan Kaufmann Publishers |year=1992 |pages=151–154, 159, 163–169, 175, 181 |isbn=1-55860-191- | * {{Citation |last=Norvig |first=Peter |title=ELIZA: Paradigms of Artificial Intelligence Programming |place=San Francisco |publisher=Morgan Kaufmann Publishers |year=1992 |pages=151–154, 159, 163–169, 175, 181 |isbn=978-1-55860-191-8}}. | ||
* {{Citation |last=Wardip-Fruin |first=Noah |title=Expressive Processing: Digital Fictions, Computer Games, and Software Studies |place=Cumberland |publisher=MIT Press |year=2014 |pages=24–36 |isbn=978- | * {{Citation |last=Wardip-Fruin |first=Noah |title=Expressive Processing: Digital Fictions, Computer Games, and Software Studies |place=Cumberland |publisher=MIT Press |year=2014 |pages=24–36 |isbn=978-0-262-51753-9}}. | ||
* {{Citation | last = Weizenbaum | first = Joseph | author-link = Joseph Weizenbaum | year = 1976 |page=6 | title = Computer power and human reason: from judgment to calculation | isbn = 0-7167-0463- | * {{Citation | last = Weizenbaum | first = Joseph | author-link = Joseph Weizenbaum | year = 1976 |page=6 | title = Computer power and human reason: from judgment to calculation | isbn = 978-0-7167-0463-8 | publisher = [[W. H. Freeman and Company]]| title-link = Computer Power and Human Reason }}. | ||
* {{Citation | last = Whitby | first = Blay | author-link = Blay Whitby | year = 1996 | contribution = The Turing Test: AI's Biggest Blind Alley? | title = Machines and Thought: The Legacy of Alan Turing | volume = 1 | editor = Millican, Peter | editor2 = Clark, Andy | publisher = [[Oxford University Press]] | pages = 53–62 | isbn = 0-19-823876- | * {{Citation | last = Whitby | first = Blay | author-link = Blay Whitby | year = 1996 | contribution = The Turing Test: AI's Biggest Blind Alley? | title = Machines and Thought: The Legacy of Alan Turing | volume = 1 | editor = Millican, Peter | editor2 = Clark, Andy | publisher = [[Oxford University Press]] | pages = 53–62 | isbn = 978-0-19-823876-8 | url = http://www.cogs.susx.ac.uk/users/blayw/tt.html | access-date = 2008-08-11 | archive-url = https://web.archive.org/web/20080619033628/http://www.cogs.susx.ac.uk/users/blayw/tt.html | archive-date = 2008-06-19 | url-status = dead }}. | ||
==Further reading== | ==Further reading== | ||
| Line 109: | Line 121: | ||
==External links== | ==External links== | ||
* [https://sites.google.com/view/elizagen-org/original-eliza ELIZAGEN] | * [https://sites.google.com/view/elizagen-org/original-eliza ELIZAGEN]—Weizenbaum's original code for ELIZA | ||
* [https://github.com/jeffshrager/elizagen.org Collection] of several source code versions at [[GitHub]] | * [https://github.com/jeffshrager/elizagen.org Collection] of several source code versions at [[GitHub]] | ||
* {{webarchive |url=https://web.archive.org/web/20130120161839/http://www.stanford.edu/group/SHR/4-2/text/dialogues.html |date=January 20, 2013 |title= | * {{webarchive |url=https://web.archive.org/web/20130120161839/http://www.stanford.edu/group/SHR/4-2/text/dialogues.html |date=January 20, 2013 |title=Dialogues with colorful personalities of early AI}}, a collection of dialogues between ELIZA and various conversants, such as a company vice president and [[PARRY]] (a simulation of a paranoid schizophrenic) | ||
* [http://www.ilmarefilm.org/archive/weizenbaum_archiv_E.html Weizenbaum. Rebel at work] {{Webarchive|url=https://web.archive.org/web/20210225134608/http://www.ilmarefilm.org/archive/weizenbaum_archiv_E.html |date=2021-02-25 }} – Peter Haas, Silvia Holzinger, Documentary film with Joseph Weizenbaum and ELIZA. | * [http://www.ilmarefilm.org/archive/weizenbaum_archiv_E.html Weizenbaum. Rebel at work]; {{Webarchive|url=https://web.archive.org/web/20210225134608/http://www.ilmarefilm.org/archive/weizenbaum_archiv_E.html |date=2021-02-25 }} – Peter Haas, Silvia Holzinger, Documentary film with Joseph Weizenbaum and ELIZA. | ||
* [https://corecursive.com/eliza-with-jeff-shrager/ CORECURSIVE #078; The History and Mystery Of Eliza; With Jeff Shrager] – Adam Gordon Bell interviews Jeff Shrager, author of the 1973/77 BASIC ELIZA, and discoverer of the original ELIZA code. | * [https://corecursive.com/eliza-with-jeff-shrager/ CORECURSIVE #078; The History and Mystery Of Eliza; With Jeff Shrager] – Adam Gordon Bell interviews Jeff Shrager, author of the 1973/77 BASIC ELIZA, and discoverer of the original ELIZA code. | ||
* [https://sites.google.com/view/elizagen-org/blog/eliza-reanimated ELIZA Reanimated] | * "[https://sites.google.com/view/elizagen-org/blog/eliza-reanimated ELIZA Reanimated]"—ELIZAGen.org blog post describing Rupert Lane's restoration of the original MAD-SLIP ELIZA running on CTSS on a 7094 emulator | ||
{{Authority control}} | |||
{{DEFAULTSORT:Eliza}} | {{DEFAULTSORT:Eliza}} | ||
[[Category: | [[Category:1960s electronic literature works]] | ||
[[Category:1966 software]] | |||
[[Category:American electronic literature works]] | |||
[[Category:Chatbots]] | [[Category:Chatbots]] | ||
[[Category:Health software]] | [[Category:Health software]] | ||
[[Category:History of artificial intelligence]] | |||
[[Category:Psychotherapy]] | [[Category:Psychotherapy]] | ||
[[Category:Public-domain software with source code]] | [[Category:Public-domain software with source code]] | ||