Book Review: Scott J. Shapiro, Fancy Bear Goes Phishing: The Dark History of the Information Age, in Five Extraordinary Hacks

 Scott Shapiro's 2023 book's aim is to answer three questions: (1) why is the Internet (still) so insecure? (2) how do hackers do what they do? and (3) what can be done about it? He recounts some historical events, the "five extraordinary hacks" of the subtitle, to tell the story, and introduces the terms "upcode" and "downcode" as the core concepts in his framework for understanding--where "downcode" means actual, implemented computer code and "upcode" means the social, political, and institutional forces providing incentives and governance.  This is essentially a simplified version of Lawrence Lessig's four forces of law, social norms, markets, and code spelled out in his 1999 book, Code: And Other Laws of Cyberspace, and also reminded me of the framework in Bruce Schneier's 2012 book, Liars and Outliers: Enabling the Trust That Society Needs to Thrive, where the four forces are moral pressures (internalized incentives), social pressures (social/cultural incentives from other people), institutional guidelines and rules (formal rules, regulations, and laws), and security systems (locks, police, firewalls, fraud detection, etc. -- actual operational controls which may be implemented physically, in code, or by policies and practices). For Shapiro, Lessig's first three forces are "upcode" and only code is "downcode," and Schneier's first three forces and parts of his fourth are "upcode."

I found Shapiro's answers to the first and last questions of his project fairly unsatisfying by comparison to Schneier's book (or to, say, Ross Anderson's massive Security Engineering book, which you can find free online and which is the number one book I recommend to people interested in computer security). His upcode/downcode framework is, I think, too simplistic, and while he correctly identifies some of the specific factors relevant to his five extraordinary hacks, he also makes some bad arguments and gets some things quite wrong, and I think misses some of the key issues that have become highly relevant today with the rise of large language models (LLMs).

His answers to the second question, specific to the hacks he describes, however, are generally quite good and detailed, and this is where I think the book is at its strongest.  The five hacks are:

(1) The Robert Morris Jr. worm.  (2) Dark Avenger's viruses.  (3) The breach of Paris Hilton's T-Mobile Sidekick. (4) The Russian GRU (CrowdStrike name: "Fancy Bear") breach of the DNC and DCCC.  (5) The DDoS attacks of the Mirai botnet.

Each hack is presented over multiple chapters, with historical context and explanation of technical details, as well as relevant social and psychological (and legal) factors, in his upcode/downcode framework. I share a complaint with other reviews that Shapiro has a tendency to invent unnecessary terminology ("vorms" for a virus/worm hybrid, and "mudges" for malicious nudges, of the sort commonly referred to as "dark patterns" or that are examined in depth in Natasha Schüll's 2012 book, Addiction by Design: Machine Gambling in Las Vegas).

My biggest factual complaints with Shapiro come in some of the background context he supplies to the 1988 Morris worm, when he gives a brief history of the UNIX operating system that begins with its predecessor, Multics. Shapiro notes that his father, like Morris's, worked at Bell Labs. (And disclosure: I used Multics beginning around 1978-79 and as a Multics developer from 1983-1989.) Bell Labs is the likely source of the issues in Shapiro's discussion of Multics. Shapiro describes the history of Multics like this (p. 26):

A large team from MIT, Bell Labs, and General Electric, therefore, decided to develop a complete multiuser operating system as a replacement for batch processing. They called it Multics, for Multiplexed Information and Computing Service.

   The Multics team designed its time-sharing with security in mind. Multics pioneered many security controls still in use today--one of which was storing passwords in garbled form so that users couldn't repeat Allan Scherr's simple trick. After six years of development, Multics was released in 1969.

   The military saw potential in Multics. Instead of buying separate computers to handle unclassified, classified, secret, and top-secret information, the Pentagon could buy one and configure the operating system so that users could only access information for which they had clearance. The military estimated that it would save $100 million by switching to time-sharing.

   Before the air force purchased Multics, they tested it. The test was a disaster. It took thirty minutes to figure out how to hack into Multics, and another two hours to write a program to do it. "A malicious user can penetrate the system at will with relatively minimal effort," the evaluation concluded.

   The research community did not love Multics either. Less concerned with its bad security, computer scientists were unhappy with its design. Multics was complicated and bloated--a typical result of decision by committee. In 1969, part of the Multics group broke away and started over. This new team, led by Dennis Ritchie and Ken Thompson, operated out of an attic at Bell Labs using a spare PDP-7, a "minicomputer" built by the Digital Equipment Corporation (DEC) that cost ten times less than an IBM mainframe.

   The Bell Labs team had learned the lesson of Multics' failure: Keep it simple, stupid.

Based on this description, one might infer that the US Air Force did not purchase Multics and that it faded away, but in fact they purchased multiple Multics systems and operated them for decades. One might also infer that the Paul Karger and Roger Schell-led penetration test was the end of the story, when it was just the beginning--the issues identified were corrected, and on September 1, 1985, Multics was the first operating system to receive a B2 security rating from the National Computer Security Center (a project I participated in). Shapiro's "thirty minutes to figure out how to hack" and "another two hours to write a program to do it" is referring to the "Master Mode Transfer" vulnerability in table 3 of the Karger and Schell report, and it should be noted that these time estimates are for a computer science graduate of a major university with moderate knowledge of Multics design and nine months experience as a Multics programmer with access to the source code (which Multics provided to its customers for all except the "unbundled" extra-cost software). Shapiro's "A malicious user can penetrate the system at will with relatively minimal effort" is an accurate quote from the report, but not from its conclusion, rather, from an earlier section titled "Multics as a Base for a Secure System" that is referencing the prior section, "Multics is not Now Secure." The next section says that "In the long term, it is felt that Multics can be developed into an open secure multi-level system by restructuring the operating system to include a security kernel." And that was, in fact, done -- the B2 security rating was earned, in part, for demonstration of the security of the Multics Trusted Computing Base (TCB), aka, the "kernel."

Shapiro's description says that Multics was "complicated and bloated." While it is true that some joked that Multics stood for "many unnecessary large tables in core [memory] simultaneously," it was incredibly small and streamlined by modern standards. Karger and Schell's followup paper, "Thirty Years Later: Lessons from the Multics Security Evaluation," notes that the 1973 Multics TCB was 628K bytes, and that the security policy alone of SELinux is 2.5 times larger, not even counting the Linux kernel itself.

It is also worth noting that while Shapiro's description suggests that the Bell Labs team broke away and started afresh after this failure, Bell Labs actually withdrew from Project MAC very early in the project, in March 1969, while the Air Force assessment took place from July 1972 to October 1973. Ken Thompson has admitted in an interview that he's never used a Multics system.

It is undeniably true that UNIX outcompeted Multics, but the reasons for this are many and include that Honeywell had three mainframe operating systems, GCOS (formerly GECOS), Multics, and CP-V (and its successor CP-6), and GCOS was the one that was given the most support, development, and marketing resources. Unlike UNIX, which became open source in the early nineties and its essentials cloned as the open source Linux, Multics was not made open source until November 2007 and never ported to alternative hardware. I highly recommend that anyone interested in operating system history and computer security spend some time perusing Tom Van Vleck's Multicians website, as there are still lessons to be learned about Multics. (And you can now run one yourself on a laptop or even a Raspberry Pi, via Honeywell DPS8 hardware emulation.)

A few pages later (pp. 29-30), Shapiro writes again about Multics, and rightly gives credit to the Karger and Schell report for something UNIX co-creator Ken Thompson regularly is given credit for coming up with:

When Ken Thompson won the Turing Lifetime Achievement Award in 1984, the highest honor in the computer-science community, for developing UNIX, he devoted his lecture to cybersecurity, a first for the Turing lecture. In the first half of his lecture, Thompson describes a devious hack first used by air force testers when they penetrated the Multics system in 1974. They showed how to insert an undetectable "backdoor" in Multics. ... The moral Thompson drew was bracing: the "only program you can truly trust is the one you wrote yourself."

Thompson's lecture, published as "Reflections on Trusting Trust," ends with an acknowledgement in footnote four that he didn't come up with this idea, citing "Unknown Air Force Document" (which is the first Karger and Schell document linked above). The specific idea is not just a trapdoor or trojan horse, but a trapdoor in the compiled code that is not present in the source code, but is inserted by the compiler itself -- including that insertion functionality itself being automatically inserted into the compiler when the compiler itself is recompiled. The idea is that the trapdoor cannot be observed in the source code, it's not present there, but is only in the compiled binary. Karger and Schell describe it like this (in section 3.4.5, "Trap Door Insertion"):

Clearly when a trap door is inserted, it must be well hidden to avoid detection by system maintenance personnel. Trap doors can best be hidden in changes to the binary code of a compiled routine. Such a change is completely invisible on system listings and can be detected only by comparing bit by bit the object code and the compiler listing. However, object code trap doors are vulnerable to recompilations of the module in question. ...

It was noted above that while object code trap doors are invisible, they are vulnerable to recompilations. The compiler (or assembler) trap door is inserted to permit object code trap doors to survive even a complete recompilation of the entire system In Multics, most of the ring 0 supervisor is written in PL/I. A penetrator could insert a trap door in the PL/I compiler to note when it is compiling a ring 0 module. Then the compiler would insert an object code trap door in the ring 0 module without listing the code in the listing. Since the PL/I compiler is itself written in PL/I, the trap door can maintain itself, even when the compiler is recompiled. 

An object code compiler trap door, therefore, would mean that you can't even trust a program you wrote yourself! There is, however, a route to addressing this problem, which was the subject of David A. Wheeler's doctoral dissertation in 2009, "Fully Countering Trusting Trust Through Diverse Double-Compiling."

Shapiro does mention the NCSC security certification process in his "The Lesson of the Morris Worm" section, and I think he draws the wrong lessons from it by focusing on an incomplete certification and ignoring a completed one, as well as more recent academic research (langsec) that is becoming highly relevant in the age of LLMs.  But first, one of his lessons (p. 43) is that his first question was malformed, that the Internet has to be open and purely a transport layer (the "end-to-end principle") and that the right question instead is to ask why endpoint computers are so insecure. That's clearly too quick a move, as we've seen countries build national firewalls and organizations deploy all manner of network-based security controls, and in the case of DDoS attacks, they need to be outside of the targeted victim's network (preferably geographically distributed with AnyCast to diffuse the attack traffic and to filter it before it reaches the victim's network). We also should be free to raise questions about provider liability for being sources of attack (or even "attractive nuisances").

About the NCSC security certification process, Shapiro writes (pp. 44-45):

The story of the VAX VMM Security Kernel demonstrates the pitfalls of this strategy [assessing security and certifying]. In 1979, Major Roger Schell led a team to create an operating system that could withstand the NSA's most rigorous tests and achieve the highest possible score from the NSA--an A1 rating. To do so, his team built the system in a secured laboratory so that only the development group could enter. The machine they coded on--the development machine--was housed in a separate locked room within the lab. That locked room was protected by a cage. ...

    It took a decade to build the system. By late 1989, the VMM Security Kernel was put in the field to undergo testing at government and aerospace installations. But in March 1990, DEC, the maker of the VAX minicomputer, canceled the project and removed prototypes from the testing sites. ...

 He goes on to contrast with free and open-source software, noting the risk of backdoors and "Linus's law, which holds that with enough eyeballs, all bugs are shallow (i.e., easy to find)." We know that this is not quite accurate -- you need enough appropriately experienced eyeballs, pointed in the right places, which LLMs now have the potential to do, and seem to be ramping up rapidly on. But to my mind, he should have picked a different example than the VAX VMM Security Kernel, namely Honeywell's SCOMP (Secure Communications Processor) and its STOP operating system, which received an NCSC A1 security rating in 1985. When Groupe Bull acquired Honeywell's Large Computer Products Division in 1987-1991, the SCOMP division, Honeywell's Secure Computing Technology Center based in Minneapolis, was spun out into Secure Computing, and later acquired by McAfee. The STOP operating system was ported to other hardware and used for several military-grade communications gateways (and lessons learned from it were used in other products such as the Sidewinder firewall).

The main principle for an A1 security rating is that the system have "verified design," which includes formal specification, formal verification, mandatory and discretionary access control, configuration management, and distribution control. These are high-effort, resource intensive things to produce, but they are also things that are becoming more feasible to produce with LLM assistance (and perhaps necessary to produce to mitigate more vulnerabilities becoming shallow and discoverable, and possibly helpful in addressing limitations of LLMs themselves in a virtuous circle). It's worth noting here that in the Epilogue of the book, Shapiro gives an argument for the impossibility of "a magic app that checks programs for vulnerabilities" (p. 325), basically pointing out the issue of the halting problem and Turing computability. It's certainly correct that you can't build a system that will find all bugs, but it doesn't follow from that that you cannot build systems that find many bugs, nor that you cannot eliminate entire classes of vulnerability, nor that you cannot build specialized systems that have verifiable security properties. One of the lessons of langsec is that we can do things without Turing-complete systems, and we should do so, and this is something else that LLMs might make more feasible rather than relying on general purpose operating systems for every task and function. (Book recommendation for those who draw too-broad conclusions from theorems of undecidability, computability, and incompleteness: Torkel Franzen's 2005 book, Gödel's Theorem: An Incomplete Guide to Its Use and Abuse.)

To end on a positive note, I thought that Shapiro's coverage of the book's title hack, the Russian GRU ("Fancy Bear")'s breach of the DNC and DCC, was excellent in clearly laying out the details and timeline, and citing relevant sources that support the attribution. This occurs in chapters 7 and 8 (pp. 186-237), which should be mandatory reading for anyone who is still arguing that there is no evidence that Russia was behind the DNC hack or the subsequent data leaks in the face of massive evidence to the contrary. (It prompted me to add a reference to the book in my unpublished letter to the editor of Fortean Times in response to a columnist who should be mandated to read these chapters.)

Despite my issues with Shapiro's coverage of Multics and some of his conclusions, I enjoyed the book and recommend it for those interested in the history and context of the five hacks he covers.

Wikipedia, Skeptical Inquirer, and AI on Robert A. Baker plagiarism accusations

 The Wikipedia entry for University of Kentucky psychologist and skeptic Robert A. Baker recently (December 2023) restored a section on plagiarism accusations against him, which originated in a 1994 letter to the editor of Skeptical Inquirer from Jody Hey and were compounded by further accusations by Terence Hines and by me the same year. Unfortunately, the Wikipedia entry currently leaves the debate the same way the Skeptical Inquirer did in 1995, giving Baker the final word with a transparently false explanation.  Here's how the Wikipedia entry currently presents the issue:

Readers of Skeptical Inquirer, noticed in 1994 similarities between one of Baker's articles and William Grey's article Philosophy and the Paranormal, Part 2. After discovering this, Baker wrote to Grey apologizing for "forgetting both the direct quotation and the reference citation", he claims that it was an oversight. Grey publicly accepted Baker's apology in the Skeptical Inquirer.^[20] In the following year, author Terence Hines accused Baker of unattributed quotations from an article by Melvin Harris and from his own book Pseudoscience and the Paranormal.^[21] Baker responded in Skeptical Inquirer. stating that he used Melvin Harris' book Investigating the Unexplained as a source, rather than the article or Hines' book, and that he gave Harris credit but forgot the quotation marks.^[22]

This description is faulty in that it omits most of the evidence and is inconsistent with it [Added 7 March 2025: --including that Grey, not Baker, discovered the issue and reported it in a letter to the Skeptical Inquirer editor.]. The most detailed account can be found in my 1994 report given to leaders at the Committee for the Scientific Investigation of Claims of the Paranormal (CSICOP, now the Committee for Skeptical Inquiry or CSI) and subsequently published in 1995 to Usenet and its update. I've also assembled a chronology of events that led to my involvement and included legal threats from Baker, which I've now updated to include a letter from Paul Kurtz in his role as head of Prometheus Books noting that Baker's book Hidden Memories had been withdrawn from publication. While I've not exhaustively searched Baker's work, I found fairly consistent plagiarism in his books for Prometheus and his book reviews for Skeptical Inquirer throughout his career as a skeptic.

The rest of this post will first show that Baker's claim to have used Harris as a source, but not Hines, is false--there is clear evidence that Baker plagiarized Hines, whose book he did not cite (and his text matches Harris's article rather than the book where they differ). Second, it will show the heaviest section of plagiarism I identified in another Baker book, They Call It Hypnosis (1990, Prometheus Books). Finally, it will show that Baker's institution defined research misconduct in a way that includes what he did, and that Baker's own writing shows that he understood this to be misconduct.

The exchange between Hines and Baker in the pages of the July/August 1995 Skeptical Inquirer (pp. 44-46) focuses on a passage on p. 157 in chapter 4 of Baker's book, Hidden Memories: Voices and Visions from Within (1992, Prometheus Books) and its resemblance to a passage on p. 74 in Hines' book, Pseudoscience and the Paranormal (1988, Prometheus Books) where he quotes from p. 23 of an article by Melvin Harris, "Are 'Past-Life' Regressions Evidence of Reincarnation?", Free Inquiry, Fall 1986, vol. 6, no. 4, pp. 18-23 (quotation marks as given in Hines):

"...every single piece of information given by Jane Evans can be traced to de Wohl's fictional account. She uses his fictional sequences in exactly the same order and even speaks of his fictional characters, such as Curio and Valerius, as if they had been real."

Hines notes that Baker uses nearly the same words in the same sequence, without quotation marks or references, on p. 157 of Hidden Memories:

Every single piece of information given by Mrs. Evans could be traced to De Wohl's book, and Mrs. Evans used his fictional sequences in exactly the same order as he had, and even spoke of De Wohl's fictional characters, Curio and Valerius, as if they had been real.

Here is how Harris makes the same statement on p. 162 of his book, Investigating the Unexplained (1986, Prometheus Books), which Baker claims is his source (italics in original):

In the same way every single piece of information given out by Jane Evans can be traced to De Wohl's fictional account. She uses his fictional sequences in exactly the same order and even speaks of his fictional characters--such as Curio and Valerius--as if they were real people.

Harris's article (p. 23):

In the same way, every single piece of information given by Jane Evans can be traced to De Wohl's fictional account. She uses his fictional sequences in exactly the same order and even speaks of his fictional characters, such as Curio and Valerius, as if they were real people. 

Baker's wording omits the "out" in the first sentence, uses commas instead of hyphens, and doesn't use the italicization, all matching the article rather than the book.

Baker cites neither Harris nor Hines in the notes for chapter 4 of his book. He does mention Melvin Harris twice on the page with no citation and no attributed quotations, including once in the same paragraph as the above quotations. Baker's discussion of other cases earlier in the chapter differs from Hines and Harris--all three discuss Bridey Murphy, but Baker's case is more extensive than Harris or Hines. I suspect his sources may be identifiable from the other references he gives at the end of the book for the chapter.

But when it comes to Baker's discussion of Jane Evans, he engaged in more plagiarism of Hines, as can be seen by comparing his text to Hines and to Harris's article and book. Harris discusses the case extensively on pp. 155-163 of his book, while Hines' and Baker's discussions are each less than two pages long.

Here is what Baker writes (pp. 156-157), with exact word matches with Hines highlighted in yellow, and with Harris' article in orange (and I found no matches to Harris's book which did not also match the article):

The second, and by far the most [Harris: much more] impressive, was the case of a Welsh housewife named Jane Evans, who described six past lives that were remarkable for the tremendous amount of accurate historical detail [Harris: amount of detail] they contained. In one of the lives she was a maid in the house of a wealthy [Baker, p. 157:] and powerful merchant in fifteenth-century France. Mrs. Evans described accurately the house and all of its furnishings in great detail, as well as the members of the merchant's family. She made one very significant error in her account, however. She said the merchant was unmarried [Hines: not married] and had no children. In truth he was married and had five children, circumstances no maid would be unaware of. The same failure to mention wife and children turned up in a novel that had been written about the merchant, titled The Moneyman by Thomas B. Costain (1948). According to Melvin Harris, who investigated the case, the evidence is overwhelming that this book was the source of all of Mrs. Evan's [sic; Hines: basis for Evans's] "memories" of her life in fifteenth-century France.

   In another life that she reported, Mrs. Evans was a woman named Livonia, who lived during the Roman occupation of Britain. Her account [Hines: knowledge] of the historical facts of this [Hines: that] period was so accurate that authorities [Harris: authority] on Roman Britain were astounded. Again, however, there were a few factual errors. Her knowledge [Hines: information] of the period was traced to the 1947 best-selling novel The Living Wood by Louis De Wohl. Every single piece of information given by Mrs. Evans could be traced to De Wohl's book, and Mrs. Evans used [Hines, Harris: she uses] his fictional sequences in exactly the same order as he had, and even spoke [Hines, Harris: speaks] of De Wohl's [Hines, Harris: his] fictional characters, Curio and Valerius, as if they had been [Hines, Harris: were] real. The historical errors in Mrs. Evan's [sic] account were also found in the book. As Harris clearly demonstrated, Mrs. Evans had [Harris: had] the ability to store vivid stories in her subconscious and then creatively combine and edit them to the point that [Harris: where] she herself became [Harris: becomes] a [Harris: one of the] character in the story [Harris: involved].

This last sentence is another in which Baker follows Harris's article more closely than his book, which suggests Baker used the article in addition to Hines (who doesn't quote this sentence).  Harris's book (p. 161) says "... Jane Evans has the ability to subconsciously store vivid accounts and combine and edit these creatively--to the point where she becomes one of the characters involved." The article (p. 22) says "...Jane Evans has the ability to store vivid stories in her subconscious and creatively combine and edit them to the point where she becomes one of the characters involved."

Overall, Baker follows Hines more closely than Harris, and when there are discrepancies between Harris's article and book, Baker follows the article.  While Harris names the maid (Alison), neither Hines nor Baker do. In structure, after introducing the maid, Hines and Baker mention Evans' description of the house and furnishings, but Harris only mentions that after describing Evans' "inside-knowledge of the intrigues surrounding the King's mistress, Agnes Sorel," which Hines and Baker omit. The sentences from Hines and Baker that immediately follow the house and furnishings differ slightly in wording but are strikingly similar:

Hines (p. 73): "Evans' account of her life in Coeur's house contains one most puzzling, and significant error. She says he was not married and had no children. But he was married and had five children--not the sort of thing the maid would be likely to overlook."

Baker (p. 157): "She made one very significant error in her acccount, however. She said the merchant was unmarried and had no children. In truth he was married and had five children, circumstances no maid would be unaware of."

Harris, by contrast, is quite different (p. 22): "In particular, the novel very neatly answers an important question raised by Iverson and other commentators: Why doesn't Alison know that her master is married? As Iverson puts it: 'How is it that this girl can know Coeur had an Egyption bodyslave and not be aware that he was married with five children?--a published fact in every historical account of Coeur's life?...If the explanation for the entire regression is a reading of history books in the twentieth century, then I cannot explain how Bloxham's subject would not know of the marriage.'"

For completeness, here's Harris's book, which differs very slightly (p. 158): "In particular, the novel very neatly answers an important question raised by Iverson and other commentators--a question prompted by the curious fact that Alison does not know that her master is married! As Iverson puts it: 'How is it that this girl can know Coeur had an Egyptian bodyslave and not be aware that he was married with five children?--a fact published in every historical account of Coeur's life? ... If the explanation for the entire regression is a reading of history books in the twentieth century, then I cannot explain how Bloxham's subject would not know of the marriage.'"

In short, Baker plagiarized Hines and Harris, and his explanation is not consistent with the facts, with the truth revealed in much the same way as the truth was revealed about Evans' stories being sourced from fiction.

Next, we turn to Baker's They Call It Hypnosis, where Baker repeatedly plagiarized sources word-for-word without quotation marks, sometimes referencing them in the chapters where used, sometimes not referencing them in the chapter, and sometimes not referencing them at all (see my full report for more examples of each). In these examples, Baker lifts from work by Nicholas P. Spanos, by Spanos and co-author John F. Chaves, and by Irving Kirsch and James R. Council, with his only original contributions being some introductory or connecting phrases and substitution of synonyms. Here is what appears on pp. 129-131 of They Call It Hypnosis, part of chapter three titled "Hypnosis: Recent and Contemporary Views," with highlights indicating word-for-word plagiarism from the sources used:

     [Baker, p. 129] Overall, Spanos's position on hypnosis is very clear. He argues that, despite widespread belief to the contrary, hypnotic procedures do not greatly augment responsiveness to suggestions. Nonhypnotic control subjects who have been encouraged to do their best respond just as well as hypnotic subjects to suggestions for pain reduction, amnesia, age regression, hallucination, limb rigidity, etc. Hypnotic procedures, he says, are no more effective than nonhypnotic relaxation procedures at reducing [Spanos: lowering] blood pressure and muscle tension or affecting [Spanos: effecting] other behavioral, physiological, or verbal report indicators of relaxation. Hypnotic procedures are no more effective than various nonhypnotic procedures at enhancing imagery vividness or at facilitating therapeutic change for such problems as chronic pain, phobic response, cigarette smoking, etc. The available scientific evidence that Spanos and his collaborators have compiled fails to support the notion that hypnotic procedures bring about unique or highly unusual states of consciousness or that these procedures facilitate responsiveness to suggestion to any greater extent than nonhypnotic procedures that enhance positive motivation and expectation. [Spanos, p. 175]

     Spanos also notes that hypnotic suggestions do not directly instruct the subject to do anything. Instead, they [Spanos: suggestions] are usually phrased in the passive voice and imply that something is happening; for example [Spanos: e.g.], "Your arm is rising," instead of "Raise your arm." The [Spanos: This] passive phrasing communicates the idea that the suggested effects are occurring [Spanos: happening] automatically. In other words, the hypnotic suggestions are really tacit requests to the subject to become [Baker, p. 130 begins:] involved in a make-believe activity. Good hypnotic subjects understand this [Spanos: the implications of these tacit requests] and use their imaginative abilities and acting skills to become absorbed in the make-believe activities [Spanos: scenarios]. Spanos notes that the method actor who throws himself into the role is the analogue of the good hypnotic subject who throws himself [Spanos: themselves] into generating the experiences relevant to his [Spanos: their] role as someone who is hypnotized and responsive to suggestions. [Spanos, pp. 175-176]

     Spanos and his collaborators have looked closely at hypnotic age regression and have demonstrated that regressed subjects do not, in any real sense, take on the cognitive, perceptual, or emotional characteristics of actual children. Instead of behaving like real children, age regressed subjects behave the way they believe children behave. To the extent that their expectations about how children behave are inaccurate, their age regression performances also are off the mark. Simply put, age regression suggestions are invitations to become involved in the [Spanos: this] make-believe game of being a child again. People who accept the invitation do not, in any literal sense, revert psychologically to childhood. Instead, they use whatever they know about real children, whatever they remember from their own childhood, to temporarily become absorbed in the fantasy of being a child again. [Spanos, p. 176]

     Just as subjects can be given suggestions for age regression, amnesia, or pain reduction, Spanos says they can also be led to believe that they possess "hidden selves." When Hilgard's good hypnotic subjects were told [Spanos: informed] that they possessed hidden selves they normally were unaware of--but to which the experimenter could talk when he gave [Spanos: by giving] the proper [Spanos: appropriate] signals--many of them [Spanos: these subjects], when the signals were given [Spanos: they received], acted [Spanos: behaved] as if they did have alternate egos [Spanos: possessed secondary selves]. Hilgard interpreted this as indicating [Spanos: interpret such findings to mean] that good hypnotic subjects carry around unconscious hidden selves with certain intrinsic, unsuggested characteristics. Spanos counters this by pointing out that the evidence shows these [Spanos: indicates instead that] so-called hidden selves are neither intrinsic to hypnotic procedures nor unsuggested. On the contrary, hidden self-performances--like other suggested responses--appear to reflect attempts by motivated and imaginative subjects to create the experiences and role-play the behaviors [Spanos: role behaviors] called for by the instructions they are given. By the experimenter varying these [Spanos: such] instructions, the subjects can be easily led to develop hidden selves with whatever characteristics the experimenters desire [Spanos: wish]. Depending upon the instructions given, good hypnotic subjects will act out [Spanos: enact] hidden selves reporting [Spanos: that report] very high levels of pain, very low levels of pain, or both high and low levels of pain in succession. Subjects can also be led to act as if they possess hidden selves that can remember concrete but not abstract words, or the opposite; or they can report seeing [Spanos: that see] stimuli accurately, seeing them [Spanos: see stimuli] in reverse, or not seeing them [Spanos: don't see stimuli] at all; as the experimenter wishes. In short, the subjects are [Spanos: subject is] acting out a fantasy which is initiated by the suggestions of the hypnotist. Then the fantasy is imaginatively elaborated upon and sustained by the subject and his interactions with the hypnotist. [Spanos, pp. 176-177]

     [Baker, p. 131 begins:] Spanos has also carried out studies of past-life regression, and in agreement with the findings of other researchers, his work indicates that past-life reports from hypnotically regressed subjects are fantasy constructions of imaginative subjects who are willing to become absorbed in the make-believe situation implied by the regression suggestions. As expected, subjects who responded well to other hypnotic suggestions were the most likely to respond well to regression suggestions. Those with the most practice at vivid daydreaming and everyday fantasizing, i.e., the fantasy-prone, created the most vivid past-life fantasies. In the same manner as childhood regressees, past-life reporters incorporate historical misinformation into their past lives [Spanos: -life enactments]. Those who from the outset believed in reincarnation thought their past lives were true [Spanos: -life experiences were veridical] rather than imaginary. A lengthier discussion of this topic and other paranormal hypnotic beliefs will be found in a later chapter. [Spanos, p. 179]

     By no means, however, does Spanos see the problem of hypnosis as solved. New knowledge leads us to new unknowns and in the well-known and pronounced effects of suggestion on the human body there are many unsolved problems. The suggestion-induced disappearance of warts, for example, is just such a dilemma. Spanos's own work has shown that neither a hypnotic induction nor preliminary instructions for relaxation add to the effectiveness of imagery-based suggestions in producing wart regression. Nor can the effects of suggestion be accounted for simply in terms of enhanced expectancies. Subjects given placebos and those given suggestions reported equivalent expectations of treatment success, but the suggestions were much more effective than the placebos in [Spanos & Chaves: at] producing wart regression. The suggestions, however, were not effective with all the subjects. They were most effective, Spanos reports, with subjects who had [Spanos & Chaves: possessed] multiple warts rather than [Spanos & Chaves: as opposed to] single warts. Those who rated their suggested imagery as especially [Spanos & Chaves: relatively] vivid also had better results. [Spanos & Chaves, pp. 445-446]

At this point, Baker says "Spanos concludes that" followed by a large block of correctly cited and quoted text from Spanos & Chaves p. 446 that fills the rest of p. 131, with a concluding sentence on p. 132 that appears to be original. Baker goes on in pp. 132-134 to describes the views of Irving Kirsch under the heading "Irving Kirsch and Response Expectancy in Hypnotic Behavior," with an original opening paragraph that cites Irving Kirsch, "Response expectancy as a determinant of experience and behavior," American Psychologist 1985, vol. 40, pp. 1189-1202, a source he does not plagiarize. But he goes on to plagiarize a source that he cites nowhere in his book, Kirsch & Council's chapter from Spanos & Chaves' book (which book he does list as a reference at the end of the chapter, but doesn't cite in the section). There is more original content in this section, and more extensive rewriting, but the level of plagiarism increases as it goes on:

[Baker, p. 132:] In the latter part of the nineteenth century, Albert Moll argued [Kirsch & Council, p. 360: maintained] that hypnotic behavior was determined by two basic principles: 1) people [Kirsch & Council, quoting Moss, 1897, p. 241: men] have a certain proneness to allow themselves to be influenced by others through their ideas, and in particular, to believe much without making conscious logical deductions; 2) a psychological effect tends to appear in a person [Kirsch & Council, quoting Moss, 1897: man] if he is expecting it. Moll also was able to cause his [Kirsch & Council: elicit hallucinations by leading] blindfolded subjects to hallucinate when he told them [Kirsch & Council: to believe] they were being mesmerized.

   Moll's giving expectancy a role in the production of hypnotic phenomena anticipated Kirsch's thinking that response expectancies cause [Kirsch & Council, p. 361: generate corresponding] the individual to have internal subjective experiences which then cause [Kirsch & Council: and their] behavior [Kirsch & Council: behavioral and physiological correlates]. A very clear [Kirsch & Council: particularly apparent] example of this is the placebo effect. When the patient is given a sugar pill but is told or believes it is a powerful pain killer, miraculously, because of his expectancies, the pain goes away! As for hypnosis, according to Kirsch, the occurrence of a hypnotic response is a function of the subject's expectancy that it will occur. Once the subject has learned how a hypnotized subject is supposed to react and what he can expect to happen when he is hypnotized, then the hypnotic responses occur automatically, i.e., without conscious effort on the subject's part. Emotional reactions--fear, sadness, sexual arousal, pain--are good examples of automatic responses. Acrophobics, for example, will avoid tall buildings, cliffs, ferris wheels, etc., because of their expectancy that not doing so would result in a panic attack. 

   Various other evidence [Kirsch & Council, p. 362: A considerable body of data] is available to demonstrate that automatic [Kirsch & Council: nonvolitional] responses can be brought about [Kirsch & Council: elicited] by the mere expectancy of their occurrence. Both hypnosis and placebos are effective in treating pain, skin conditions, and asthma, and it seems reasonable to assume that the same mechanism, namely, response expectancy, produces these responses in both hypnosis [Baker, p. 133:] and the nonhypnosis situations. Telling subjects [Kirsch & Council, p. 364: informing them] they have received [Kirsch & Council: were ingesting] a psychedelic drug that will produce hallucinations causes about half [Kirsch & Council: 50 percent] to report visions, even though no drug was given. Subjects [Kirsch & Council: people] who are told that hypnotized subjects can't move their [Kirsch & Council: display catalepsy of the] dominant arm are likely to experience this effect when hypnotized, and being told [Kirsch & Council: informed] that inability to remember, i.e., spontaneous amnesia, is characteristic of hypnosis significantly increases the likelihood of its occurrence. When subjects were told that either the ability or the inability to resist responding to suggestions was characteristic of deep hypnosis, they responded accordingly.

   Besides affecting overt responses, role perceptions are an important determinant of self-reported experiences of altered states of consciousness. In a number [Kirsch & Council, p. 365: series] of studies it was shown [Kirsch & Council: this has been convincingly demonstrated] that the degree of change in state of consciousness subjects expected to experience significantly predicted the number of unsuggested alterations in experience they subsequently reported. Moreover, the data from these studies indicate [Kirsch & Council, p. 366: suggest] that no particular state of consciousness can be labeled a "hypnotic trance." Rather, a variety of changes in experience are interpreted by the subject as evidence of trance when experienced in a hypnotic context. Some of these are directly suggested in typical hypnotic induction--relaxation, for example [Kirsch & Council, p. 367: e.g.]--whereas others occur as a function of the subject's preconceptions. How the subject perceives the situation pretty much determines how effective the situation will be in producing hypnosis. Just hearing the words, "You are becoming very, very relaxed," is enough in our culture to make most people think [Kirsch & Council, p. 368: evokes the idea] of hypnosis. Glass and Barber (1961) a few years ago set up [Kirsch & Council: devised] a highly credible clinical environment and told subjects an inert pill was a powerful hypnotic drug which would produce a state of hypnosis. In this setting the pill was as effective as a standard hypnotic induction procedure in effecting [Kirsch & Council: raising levels of] the subject's responses to suggestion.

The rest of p. 133 of Baker is two original sentences that introduce a large block of text (five full sentences) properly identified as quotation and attributed to the Spanos & Chaves book without a page reference; it is from p. 371 in the Kirsch & Council chapter. Baker p. 134 completes the Kirsch section:

According to Kirsch's [Kirsch & Council, p. 371: expectancy] theory, the probability of occurrence of a nonvolitional response varies directly with the strength of the expectancy of the occurrence and inversely with the magnitude or difficulty of the expected response. [Baker has removed Kirsch & Council's quotation marks before "the probability"; the rest of the sentence is a direct quote from Kirsch's 1985 paper.]

   Trance induction procedures are, of course, typically designed to increase the subject's expectancies for responding to suggestions, and in the Ericksonian approach [Kirsch & Council: clinical practice] the hypnotist tailors his induction to the characteristics and ongoing behavior of the client [Kirsch & Council: individual subjects]. Kirsch sees most hypnotic induction procedures as merely expectancy modification procedures.

   Kirsch's response expectancy theory [Kirsch & Council, p. 374: hypothesis] is generally consistent with the nonstate theories of Sarbin, Barber, Wagstaff, and Spanos. All agree that hypnotic responses are best seen [Kirsch & Council: can be conceptualized] as compliance, belief, and imagination [Kirsch & Council: believed-in imaginings], and that the hypnosis experience occurs when people voluntarily play [Kirsch & Council: take on] the role of hypnotic subject. One key difference between Kirsch's theory and others is that his response expectancies are the immediate causes of the hypnotic response. Rather than having goal-directed images enhancing hypnosis, as Barber suggests, Kirsch has shown that the imagery enhances responsiveness by virtue of its effects on expectancy. Kirsch has also shown that not all so-called hypnotic phenomena are under a subject's will power or self-control [Kirsch & Council, p. 378: cannot be fully accounted for as volitional behavior]. Warts, for example, can be affected both by placebos and by hypnosis, and such changes in skin conditions are not under one's voluntary control. Kirsch notes that one could offer subjects a substantial sum of money to make their warts disappear, but it is highly unlikely that many subjects would be able to do so.

This phenomenon also clearly shows [Kirsch & Council, p. 378: demonstrates] the commonality between hypnosis [Kirsch & Council: hypnotic phenomena] and placebo effects. Both are examples of the nonvolitional nature of response expectancy effects. Kirsch's observation raises another point of significance--the fact that we must realize that not everything that happens to the human being as a result of external stimulation is or should be considered hypnosis! Suggestion is a very powerful influence on human behavior and it can influence human behavior in many different ways, only a very few of which we would or should designate as "hypnotic."

Yellow highlight: Nicholas P. Spanos, "Past-Life Hypnotic Regression: A Critical View," Skeptical Inquirer vol. 12, no. 2, Winter 1987-88, pp. 174-180. Not listed as a reference in chapter three, but is listed as a reference in chapter six.

Orange highlight: Nicholas P. Spanos and John F. Chaves, Hypnosis: The Cognitive-Behavioral Perspective, 1989, Prometheus Books. This is listed as a reference in chapter three, but is not cited in the section where it is plagiarized, but instead on p. 129 a few paragraphs before the plagiarism of the Spanos SI article (yellow highlight).

Green highlight: Irving Kirsch and James R. Council, "Response Expectancy as a Determinant of Hypnotic Behavior," in Spanos & Chaves (1989), pp. 360-379. This chapter is not listed as a reference in the book.

I reviewed Baker's They Call It Hypnosis for Amazon.com on November 18, 1996, and gave it four stars; I might subtract another star today and say more about its giving state theories short shrift, but otherwise I still agree with this:

This book is an excellent summary of theories of hypnosis
with an emphasis on criticisms of state theories. The
author argues for social/cognitive non-state theories.
The book is marred only by the fact that many passages
are lifted directly from the authors being summarized,
without being noted as such.

Finally, here is the definition of research misconduct from the University of Kentucky's "Policy on Ethical Standards and Misconduct in Research" (64.0 AR II-4.0-2) from 1992:

Research "misconduct", as used herein, is defined as plagiarism; 
fabrication or intentional falsification of data, research procedures or 
data analysis; or other deliberate misrepresentation in proposing, 
conducting, reporting, or reviewing research.  It does not include 
honest error or honest differences in interpretations or judgments of 
data.  In cases of allegations involving activities submitted to or 
supported by a federal agency, the definition for misconduct specified 
in the agency's regulations will apply.

This policy was referenced in the faculty handbook section on "The Conduct of Research" in the paragraph on "Ethical Standards"; these are quoted more extensively in my full report. Baker was certainly aware of these in substance, as the following appears on p. 297 of Robert A. Baker and Joe Nickell's book, Missing Pieces: How to Investigate Ghosts, UFOs, Psychics, and Other Mysteries (1992, Prometheus Books):

Another question that is bound to arise has to do with rewriting and 
paraphrasing.  The courts once again have uniformly decided that it 
makes no difference whether the plagiarizer changes the arrangement of 
the original words or not--rewriting the material is not sufficient to 
aid the charge of infringement. ... More importantly, even if the use of 
the words and statements of another is totally honest, unintentional, or 
subconscious, it is still prohibited.  Neither forgetfulness nor 
ignorance is regarded as a legitimate excuse.  If, however, it was an 
honest and unintentional mistake, and no intent to plagiarize was in 
mind, the infringer usually gets off with a lesser punishment.

Baker's response to these allegations was at first to attack and concede nothing. He suggested that he was going to sue me for defamation, and enlisted the help of others who attempted to discredit me (see my letter to Tucson skeptic James McGaha). Ultimately, after psychologist Terence Hines, another prominent skeptic, was prepared to submit his book review of Baker's Hidden Memories, rejected by Skeptical Inquirer, to competing publication Skeptic magazine,  SI editor Kendrick Frazier relented and published the review along with Baker's reply. Baker fell back to the claim that his plagiarism was minor and unintentional, while resorting to falsehoods to attempt to prop up that explanation, as explained above. At this point, CSICOP founder and Prometheus Books head Paul Kurtz sent me a letter stating that Hidden Memories had been pulled from distribution and would not be reissued until corrections had been made; I replied noting that there were bigger problems in They Call It Hypnosis, but received no response.

Robert Baker was added to the Committee for Skeptical Inquiry's Pantheon of Skeptics honoring distinguished Fellows of the organization on its creation in 2011.

Skeptical Inquirer and Wikipedia, at least to date, both gave Baker's falsehoods the final word. And perhaps the more interesting back story here is that Wikipedia is wrong because Skeptical Inquirer is wrong, but the reason Wikipedia only even mentioned Baker's plagiarism at all in December 2023 is because a Wikipedia editor with no dog in the fight, "Psychologist Guy," intervened and restored an old edit of the article to include the mention, which had been removed in 2018 by another Wikipedia editor, "Niomart," with the false justification that "No valid source substantiating plagiarism claims".

As the Internet becomes more and more filled with AI-generated content, there will be sources with superficial plausibility generated by large language models, there will be sources that are human-curated and based on genuine research and fact-checking, and there will be sources that are human-curated and ideologically driven that settle on acceptable half-truths concealing messy details. OpenAI's ChatGPT 3.5 says it knows nothing of plagiarism by Robert A. Baker:

Did Robert A. Baker's 1992 book, Hidden Memories (pp. 156-157), plagiarize from Terence Hines' 1988 book Investigating the Unexplained (pp. 73-75)?

As of my last knowledge update in January 2022, I do not have specific information regarding an allegation of plagiarism between Robert A. Baker's book "Hidden Memories" and Terence Hines' book "Investigating the Unexplained" related to the pages specified. Therefore, I cannot definitively answer whether Baker's book plagiarized from Hines' book.

To investigate this further and obtain accurate information, I would recommend checking scholarly resources, academic databases, or reputable sources that discuss these books and any related allegations of plagiarism. You might also look into academic discussions or reviews of both books to see if there are any mentions of such accusations and their resolution.

Google Gemini quotes from and cites Wikipedia as the final word:

Was Robert A. Baker ever accused of plagiarism, or of failure to properly cite quotations and sources?

Yes, Robert A. Baker did face accusations of plagiarism in the past according to his Wikipedia page [Robert A. Baker Wikipedia].

Here's a summary of the incidents:

• In 1994, readers of Skeptical Inquirer identified similarities between Baker's article and another author's work. Baker apologized, claiming it was an oversight.
• The following year, another author pointed out unattributed quotes in Baker's writing. Baker defended himself by saying he used the original source but forgot quotation marks.

A short conversation with ChatGPT about the Grand Canyon

  ChatGPT does fairly well with this, though its selected points don't include any of the more obscure points of interest, it's skewed to the popular highlights. Its claim that there weren't any historic crossings is pretty odd.

What are some of the most beautiful and interesting locations in the Grand Canyon along the Colorado River?

The Grand Canyon offers numerous beautiful and interesting locations along the Colorado River. Here are some notable ones:

1. Havasu Creek: Located on the western side of the Grand Canyon, Havasu Creek is famous for its turquoise-blue waterfalls and pools. The stunning Havasu Falls, Mooney Falls, and Beaver Falls are among the main attractions.

2. Phantom Ranch: Situated at the bottom of the Grand Canyon, Phantom Ranch is a historic oasis accessible only by hiking or rafting. It provides a unique lodging option and serves as a hub for various hiking trails and activities.

3. Bright Angel Trail: This popular hiking trail descends from the South Rim down to the Colorado River. It offers breathtaking views of the canyon's layers, geological formations, and the river itself.

4. Hermit Rapids: Known for their tumultuous whitewater, the Hermit Rapids offer a thrilling experience for river rafting enthusiasts. These rapids are located in a remote and scenic section of the canyon.

5. Deer Creek Falls: Nestled in a picturesque alcove, Deer Creek Falls is a stunning waterfall that drops into a deep pool. The location also features the Deer Creek Narrows, a beautiful slot canyon to explore.

6. Lava Falls: Considered one of the most challenging and exciting rapids in the entire Grand Canyon, Lava Falls is a thrilling spot for experienced river runners. It provides an adrenaline-pumping adventure as you navigate through the turbulent waters.

7. Nankoweap Rapids: Located in a less visited area of the Grand Canyon, Nankoweap Rapids offer a mix of exciting rapids and serene camping spots. The views from Nankoweap Trail, which descends to the river, are awe-inspiring.

8. Redwall Cavern: This enormous natural amphitheater-like feature is carved into the Redwall Limestone cliffs. It offers a unique camping and picnic spot along the river, where groups can gather and enjoy the stunning surroundings.

Remember that exploring the Grand Canyon and its Colorado River region requires careful planning, permits, and appropriate equipment. Whether you choose to hike, raft, or simply admire the beauty from the rim, always prioritize safety and follow any guidelines or regulations set by the National Park Service.

What are some interesting human artifacts that are left behind within the Grand Canyon, either by native Americans from hundreds of years ago, from the late 19th century, or even from the 20th or 21st century?

The Grand Canyon has a rich cultural history, and various human artifacts have been left behind by different groups over the centuries. Here are some interesting examples:

1. Native American Petroglyphs and Pictographs: The canyon is home to numerous petroglyphs and pictographs created by Native American tribes who inhabited the area for thousands of years. These rock art sites provide glimpses into their cultural and spiritual practices. Key locations include the Bright Angel and Hermit Trails, Palatki Heritage Site, and Nankoweap Canyon.

2. Tusayan Ruins: Located on the South Rim, the Tusayan Ruins are the remnants of a Puebloan village that was inhabited around 800 years ago. The site includes a partially reconstructed dwelling and offers insights into the lives of the ancient inhabitants.

3. Historic Mining Sites: In the late 19th century, prospectors and miners ventured into the Grand Canyon in search of minerals and ores. Remnants of their activities, such as old mine shafts, rusted equipment, and structures, can still be found in certain areas, like the Bright Angel and South Kaibab Trails.

4. Grand Canyon Village: Established in the early 20th century, Grand Canyon Village is a historic district that features buildings constructed by the National Park Service and the Santa Fe Railroad. Many of these structures, including the El Tovar Hotel, Hopi House, and Bright Angel Lodge, reflect early 20th-century architecture and offer a glimpse into the region's tourism history.

5. Glen Canyon Dam: Although not within the boundaries of the Grand Canyon National Park, the construction of the Glen Canyon Dam in the 20th century significantly impacted the Colorado River and the Grand Canyon ecosystem. The dam created Lake Powell and led to the formation of many archaeological sites that were excavated before being flooded.

6. Modern Graffiti: Unfortunately, in recent years, some individuals have left behind graffiti or unauthorized markings on rock formations within the Grand Canyon. These acts of vandalism are strongly discouraged and are detrimental to the preservation of the natural and cultural heritage of the park.

It's important to note that many artifacts and sites within the Grand Canyon are protected by law, and it is illegal to disturb or remove them. Visitors should always respect and preserve these cultural treasures for future generations to enjoy.

What are some of the historic mining sites in the Grand Canyon?

The Grand Canyon has several historic mining sites that reflect the mining activities that took place in the late 19th and early 20th centuries. Here are a few notable mining sites within the Grand Canyon:

1. Orphan Mine: Located near the South Rim of the Grand Canyon, the Orphan Mine was an early copper mine that operated from the late 19th century until 1931. It produced copper ore, and remnants of mining structures and equipment can still be seen in the area.

2. Grandview Mine: Situated on the South Rim, the Grandview Mine was one of the most productive copper mines in the region during its operation from 1890 to 1901. Today, hikers can explore the remnants of the mine, including the rusting headframe and a few structures.

3. Hermit Mine: The Hermit Mine was established in the early 20th century and operated intermittently until the 1930s. It primarily targeted gold and copper deposits. The mine is located in the Hermit Creek drainage, and visitors can still see remnants of mining equipment and tunnels in the area.

4. Copper Canyon Mining District: Located in the western portion of the Grand Canyon, the Copper Canyon Mining District was active from the late 19th century to the early 20th century. It included several mines, such as the Copper Canyon Mine, the Cave Mine, and the Hidden Treasure Mine. These mines produced copper, gold, and silver ores.

5. Bass Lode Mine: Situated near the North Rim of the Grand Canyon, the Bass Lode Mine was an early 20th-century mine that primarily targeted copper deposits. While the mine itself is closed and inaccessible, visitors can observe remnants of the mining operations, including the stone walls and tailings.

When visiting these mining sites, it's important to remember that they are historic and protected areas. It is prohibited to remove artifacts or disturb the sites in any way. Respect the history and heritage of these mining sites by observing them from a distance and leaving everything as you find it.

What ferry or bridge crossings are there across the Grand Canyon?

As of my knowledge cutoff in September 2021, there are no ferry or bridge crossings available across the Grand Canyon itself. The Grand Canyon is a vast and rugged landscape, and the Colorado River cuts through it, making it challenging to establish direct crossings. The sheer size and depth of the canyon make traditional ferry or bridge crossings impractical.

However, there are transportation options available to cross the Colorado River in certain areas near the Grand Canyon:

1. Navajo Bridge: The Navajo Bridge is located northeast of the Grand Canyon National Park near the town of Marble Canyon. It provides a highway crossing over the Colorado River and connects Highway 89A. The original historic bridge, known as the Old Navajo Bridge, is now open to pedestrians and offers scenic views of the canyon.

2. Glen Canyon Dam Bridge: Located downstream from the Grand Canyon, near Page, Arizona, the Glen Canyon Dam Bridge carries U.S. Route 89 across the Colorado River. It provides a vital transportation link between Arizona and Utah, offering scenic views of Glen Canyon and Lake Powell.

3. Hualapai Tribe Helicopter Tours: The Hualapai Tribe, based on the western rim of the Grand Canyon, operates helicopter tours that provide aerial crossings of the canyon. These tours offer visitors a unique perspective and the opportunity to witness the breathtaking beauty of the Grand Canyon from above.

It's important to note that ferry or bridge crossings directly across the Grand Canyon are not available due to the rugged and protected nature of the park. Visitors typically explore the canyon by hiking its trails, taking scenic drives along the rim, or participating in guided rafting trips along the Colorado River within the canyon itself.

What historic bridge, ferry, or tram crossings have existed across the Grand Canyon which are no longer present, active, or usable?

To the best of my knowledge, there have been no historic bridge, ferry, or tram crossings across the Grand Canyon that are no longer present, active, or usable. Due to the challenging terrain and the vastness of the canyon itself, constructing and maintaining permanent crossings has proven to be extremely difficult.

Throughout history, there have been proposals and ideas for various types of crossings, but none of them have come to fruition. The natural obstacles posed by the deep and rugged canyon, as well as the commitment to preserving the natural beauty and integrity of the Grand Canyon, have prevented the establishment of permanent crossings.

It's worth mentioning that some temporary or seasonal crossings, such as cable trams, may have been used by specific expeditions, research projects, or construction activities in the past. However, these were typically temporary solutions and not long-lasting or widely accessible crossings.

As of my knowledge cutoff in September 2021, there are no documented historic bridge, ferry, or tram crossings that were once in place across the Grand Canyon.

What about the Bass Camp crossing, Lee's Ferry, or the U.S. Guano tramway crossing?

Apologies for the oversight in my previous response. You are correct, and I appreciate you pointing out these specific crossings. Here's some information about them:

1. Bass Camp Crossing: Bass Camp Crossing was a historic crossing on the Colorado River, located downstream from the confluence of the Little Colorado River with the Colorado River. It was primarily used by miners and prospectors in the late 19th and early 20th centuries to access mining areas along the river. However, it was not a formal bridge or ferry crossing but rather a ford where travelers crossed the river on horseback or with wagons.

2. Lee's Ferry: Lee's Ferry, located in northern Arizona, was an important historic river crossing on the Colorado River. It served as a transportation hub for early settlers, explorers, and miners traveling to and from the Colorado Plateau. John D. Lee operated a ferry service at this site from 1872 to 1910, providing a means of crossing the river for people, livestock, and goods. The area is now part of Glen Canyon National Recreation Area and is known for its scenic beauty and historical significance.

3. U.S. Guano Tramway Crossing: The U.S. Guano Tramway Crossing refers to a historic tramway system that was used to transport guano (bird droppings) from the caves located on the rim of the Grand Canyon. The tramway carried the guano across the canyon to the river, where it was loaded onto boats for further transport. The tramway operated in the early 20th century, but it is no longer in use.

These crossings played significant roles in the exploration, settlement, and mining activities in the region during different periods of history. While they may not be active or in use today, they hold historical significance and contribute to the overall cultural heritage of the Grand Canyon area.