From Science Fiction to Sudden Reality
Back in my younger years I greatly enjoyed Science Fiction, and from junior high through graduate school, I probably read a thousand or more books in that genre, captivated by the enormous range of interesting ideas presented.
My two favorite authors had originally been Isaac Asimov and Arthur C. Clarke, though they were eventually replaced by Larry Niven and Roger Zelazny. However, I also enjoyed a multitude of other SF writers, and among them there was someone calling himself Cordwainer Smith. During the 1950s and early 1960s he’d produced a relatively small but influential body of work, with his stories heavily laced with puzzling terminology and concepts, mostly set in a future history of the next few thousand years during which humanity was governed by the Instrumentality of Mankind. Since he wrote under a pseudonym and his chronicle was filled with rather bizarre but strangely self-consistent elements, members of the SF community sometimes jokingly speculated that he might actually be a time-traveler from the distant future, amusing himself by passing along various half-remembered tales of his own past eras.
Then after his 1966 death from a heart attack at age 53, his identity was revealed as Paul Linebarger, a military officer and academic specialist on East Asia, who had spent most of his career working as a psychological warfare expert for the CIA.
One of the many minor elements in his stories had been the notion of using laminated mouse-brains as computers, embedded with the complete knowledge and personality of an individual. This technology allowed space travelers and others to take along with them a complete collection of top specialists, whose expertise could be drawn upon as circumstances required. That strange concept recently came into my mind when I began to play around with the current generation of AI chatbots.
For many decades, I’d noticed the periodic waves of media hype surrounding Artificial Intelligence (AI) systems, which appeared with considerable regularity. Wild claims about the transformative power of AI were invariably followed by bitter disappointment as the technology turned out to be far less practically useful than originally suggested, so I’d become rather inured to such hype. Back a couple of decades ago, AI systems had passed the remarkable hurdle of being able to defeat the world’s best players in Chess and Go, certainly a very important achievement but one that seemed to have few practical implications for my own activities. But then a few years ago, Google’s AI-based language translation system had become remarkably effective so that I’d incorporated it into our own website and occasionally used it when reading foreign language articles on the Internet. However, that was the limit of my own AI usage.
Then in late 2022, the ChatGPT system of OpenAI was released and soon became wildly popular, attracting over 100 million worldwide users within weeks and sparking a gigantic AI technology boom that pushed the stocks of various AI companies and chipmaker Nvidia to stratospheric heights, with the latter now worth around $3 trillion. These Large Language Models (LLMs) were trained upon many billions of words of text scraped off the Internet and then could apparently respond to questions in well-formed English sentences, something that seemed likely to have useful and important applications.
But although these were exciting results for the world and scientific progress, they didn’t seem to have much applicability to my own research and writing, and this work was keeping me so busy that I never even bothered trying to test ChatGPT or any of the other rival chatbots.
Although our website contained many tens of millions of words of articles and posts along with hundreds of millions of words of comments, this total seemed orders-of-magnitude too scanty for any AI system to find useful. Anyway, so many of our authors and commenters were in such sharp disagreement about everything that their totally conflicting views would surely confuse any chatbot trying to process them for meaning.
However, just a few weeks ago I discovered I’d been mistaken about all of this. Apparently although generic AI systems must first be trained upon enormous quantities of text, once that has been achieved they can then be “focused” upon a much smaller body of content, which they will then treat as their primary source of knowledge, drawing upon it for any questions asked. Someone tested my own writings in that way, and the results were amazing to me, with the chatbot very effectively responding to queries by using information drawn from my own articles. So apparently it was easy to produce a simple chatbot that reasonably reflected my own perspective and accumulated knowledge, something that I found totally astonishing.
I have absolutely no expertise in AI and until a couple of weeks ago I’d never even once used a chatbot. But considering the very impressive results I saw, I began speculating about how that might be possible.
Consider the following thought-experiment. Suppose you had a text-analysis system and you were able to provide it with every word spoken or written by a given individual during his entire lifetime, supplemented by all the rest of the world’s information. Perhaps if the software were sufficiently powerful, it could then “simulate” that individual, saying the things he might say and responding in plausible fashion to any questions it were asked.
Obviously, the content we can provide to an AI chatbot is merely a minuscule fraction of that total accumulated lifetime of human output. But there’s no reason to expect that the quality of the simulation scales linearly with the volume of content provided, and perhaps a logarithmic scaling might be more likely. Moreover, published writings are surely far more significant than someone’s casually spoken utterances. So given these arguments, it then becomes an entirely empirical question of whether providing hundreds of thousands or millions of published words would be sufficient to produce a simulation of the writer good enough to be worth using. And at least in my own case, I think the answer is a resounding “Yes!”
My own body of writing is fairly substantial, totaling about 1.9 million words of articles, with the bulk of these produced in the last six years. And although many would surely disagree with much of my material, my work has been extremely self-consistent over time, so much so that I’d still stand behind at least 99% of everything I’ve published over the last thirty years. Thus a chatbot based upon my articles wouldn’t get confused by too many conflicting claims.
The last point seems like a very important one. My impression is that most general chatbots are created based upon an enormous scrape of as much Internet content as possible. But since a great deal of that content is contradictory or conflicting, the effectiveness of the resulting simulation might scale far less than linearly, perhaps more like the Root-N mean distance produced by a random walk. So by producing a chatbot derived from a single individual’s corpus of writing, such distorting conflicts are minimized and the results may be far more effective since they are based upon a far more coherent and aligned body of primary content. The fully coherent light of a low-watt laser can do many things much more effectively than the completely incoherent light of a powerful sun-lamp.
All these speculations can only be resolved empirically, so I had my writings fed into a ChatGPT4o system producing a customized Ron Unz Chatbot and asked it a few simple questions, comparing these responses to those of the OpenAI Generic Chatbot, with the differences being just what I would have expected. The chatbot that simulates my responses is now freely available for anyone to use, and I’m sure that others far more experienced in AI usage than myself should be able to ask it much better questions. I’d be glad to learn the results of such testing.
Generic Chatbot
Ron Unz Chatbot
Unfortunately, use of such customized chatbots apparently requires a Premium ChatGPT account, which costs $20/month, but I’ll see about trying to release a free version using a third-party system in the near future.
Apparently chatbot responses are partly stochastic so I discovered that asking the same question several times would usually produce somewhat different answers. I’ve also read that chatbots occasionally “hallucinate,” providing answers that are bizarre, fraudulent, or totally irrational, but I haven’t seen any of that, so the problem may be rare in this particular situation.
For those interested, I interrogated the two chatbots with a series of questions on all sorts of controversial topics, starting with the most famous conspiratorial controversy of modern times, namely the Kennedy assassinations of the 1960s:
The Kennedy Assassinations
“Who Killed JFK?”
Response of Generic Chatbot:
The assassination of President John F. Kennedy on November 22, 1963, has been a subject of extensive investigation, debate, and conspiracy theories. The official investigation, conducted by the Warren Commission, concluded that Lee Harvey Oswald acted alone in assassinating JFK. However, this conclusion has been widely questioned, and various alternative theories suggest the involvement of other individuals or groups.
Some of the prominent theories include:
Multiple Shooters: Some believe there was more than one shooter involved, based on the trajectory of the bullets and the location of the shots.
CIA Involvement: Some theories suggest that the CIA had a role in the assassination, possibly due to disagreements over JFK’s foreign policies.
Mafia Involvement: Others propose that the Mafia was involved, possibly due to Kennedy’s administration’s crackdown on organized crime.
Foreign Governments: There are theories that foreign governments, such as the Soviet Union or Cuba, may have been involved in the assassination.
Despite these theories, the Warren Commission’s conclusion remains the most widely accepted official account. The debate continues, and many documents related to the assassination remain classified or have only been partially released.
Response of Ron Unz Chatbot:
The assassination of John F. Kennedy (JFK) is one of the most debated events in modern history, with numerous theories about who was responsible. According to the articles by Ron Unz and others in the documents, there are several theories and considerable evidence suggesting a conspiracy rather than a lone gunman. Here are some key points from the documents:
Official Account: The Warren Commission concluded that Lee Harvey Oswald acted alone, firing three shots from the Texas School Book Depository, killing JFK. Oswald was then killed by Jack Ruby before he could stand trial.
Multiple Shooters Theory: Some key figures, including Secret Service agent Roy Kellerman and Governor John Connolly, believed there were multiple shooters. CIA Director John McCone also expressed skepticism about the lone gunman theory.
CIA Involvement: There is significant speculation about the involvement of the CIA in the assassination. John Newman, an author and former military intelligence officer, suggests that a rogue faction within the CIA, led by counter-intelligence chief James Angleton, was involved. Angleton had close ties to the Mossad, and there is evidence suggesting he might have orchestrated the cover-up.
Organized Crime and Anti-Castro Groups: Many researchers, including David Talbot and James W. Douglass, have pointed to a conspiracy involving organized crime, anti-Castro Cuban exiles, and elements within the CIA. Oswald was portrayed as a “patsy” with ties to these groups but was likely not the shooter.
Lyndon B. Johnson (LBJ): Some theories implicate LBJ in the assassination, suggesting he had the means, motive, and opportunity, particularly given his influence over the Warren Commission’s formation and proceedings.
Israeli Mossad: Another theory proposed by Michael Collins Piper in his book “Final Judgment” argues that the Mossad was involved due to JFK’s opposition to Israel’s nuclear weapons program. This theory posits that Angleton, with his Mossad connections, played a significant role.
In summary, while the official account attributes JFK’s assassination to Lee Harvey Oswald alone, there is extensive evidence and analysis suggesting a broader conspiracy involving multiple parties, including elements within the CIA, organized crime, anti-Castro groups, and possibly even high-level officials like Lyndon B. Johnson and international actors such as the Israeli Mossad. The true extent and nature of the conspiracy remain subjects of intense debate and investigation.
“Was Mossad Involved in the JFK Assassination?”
Response of Generic Chatbot:
There is no credible evidence to suggest that Mossad, the national intelligence agency of Israel, was involved in the assassination of President John F. Kennedy. The assassination, which took place on November 22, 1963, has been the subject of numerous investigations and conspiracy theories over the years. The official conclusion, reached by the Warren Commission in 1964, was that Lee Harvey Oswald acted alone in assassinating President Kennedy.
Various conspiracy theories have implicated different organizations and individuals, ranging from the CIA and the Mafia to foreign governments. However, these theories often rely on speculation and lack concrete evidence. The idea that Mossad was involved is one such theory, but it has not been substantiated by credible sources or evidence.
For a comprehensive understanding of the JFK assassination and the investigations that followed, it’s best to refer to established historical accounts and credible research.
Response of Ron Unz Chatbot:
The hypothesis that Mossad was involved in the assassination of JFK is primarily supported by Michael Collins Piper’s book Final Judgment. Piper posits that Mossad, together with its American collaborators, played a central role in the JFK assassination. This theory has been reinforced by various pieces of circumstantial evidence, including Kennedy’s significant opposition to Israel’s nuclear weapons program and his administration’s pressure on Israel regarding nuclear inspections.
Victor Ostrovsky, a former Mossad agent, claimed that Mossad had a history of targeting Western political leaders and even planned to assassinate President George H.W. Bush due to his policies towards Israel.
The theory suggests that after Kennedy’s assassination, policies that were unfavorable to Israel were quickly reversed, further supporting the idea of Mossad’s involvement due to significant strategic interests.
“Who Killed RFK?”
Response of Generic Chatbot:
Robert F. Kennedy was assassinated on June 5, 1968, by Sirhan Sirhan, a Palestinian immigrant. The assassination took place at the Ambassador Hotel in Los Angeles, California, where Kennedy was giving a speech after winning the California Democratic primary for the 1968 presidential election. Sirhan was captured at the scene and later convicted of first-degree murder. He has been serving a life sentence in prison since then.
Response of Ron Unz Chatbot:
Robert F. Kennedy was fatally shot on June 4, 1968, after giving a victory speech following his win in the California Democratic primary. The officially convicted assassin was Sirhan Sirhan, a Palestinian immigrant allegedly angered by Kennedy’s pro-Israel stance.
However, evidence and subsequent investigations have raised significant doubts about Sirhan’s sole culpability. Key points of contention include:
Powder burns indicated the fatal shot was fired from directly behind Kennedy’s head from a distance of three inches or less, while Sirhan was several feet in front of him.
Eyewitnesses and acoustic evidence suggested that at least twelve bullets were fired, despite Sirhan’s revolver only holding eight rounds.
Eyewitnesses reported seeing a security guard with his gun drawn standing behind Kennedy, who harbored a strong dislike for the Kennedys.
These discrepancies led the Los Angeles Coroner, Dr. Thomas Noguchi, to suggest the involvement of a second gunman. In late 2021, Robert F. Kennedy Jr. declared Sirhan Sirhan innocent and called for his release, reflecting ongoing skepticism about the true circumstances of his father’s assassination.
The post Laminated Mouse-Brains and the Magic of AI appeared first on LewRockwell.