Challenges to Comprehension Implied by the Logo
of Laetus in Praesens
Laetus in Praesens Alternative view of segmented documents via Kairos

2 June 2024 | Draft

Experimental AI Meta-analysis of an Academic Journal Issue

Use of facilities of ChatGPT 4 and Claude 3

-- / --


Introduction
Overview of content and focus
Challenge of authenticity in relation to spiritual intelligence
Issues of dramatic global concern
Questions asked versus Answers offered
Facilitation of contributor dialogue by AI
Indicative representation of insights in aesthetic forms
Potential musical reframing of themes of a journal issue
Potential symbolic implications of relevance to governance
Comment on technical constraints


Introduction

There is clearly a case for challenging contrasting artificial intelligence facilities with regard to the subtleties framed by the issues in a journal -- especially one dealing with controversial issues. Are there meta-perspectives to be fruitfully gleaned and cultivated from a single issue as a whole -- or from a set of such issues? The possibility follows from the widespread concern regarding the future impact of AI on social processes -- matched by the relatively neglected focus on the insights and processes potentially valuable to a knowledge based society.

This exploration emerged from comparative use of the facilities of ChatGPT 4 and Claude 3 (Opus variant) in summarizing the themes evoked in a set of 35 AI-related articles presented on this site over the past year (Eliciting Experimentally an Overview by AI of AI-related Articles, 2024). This developed into a comparison of the two artificial intelligence facilities with respect to global modelling -- especially from a psychosocial perspective. The extent of the responses to this distinctive focus suggested that it would be more appropriate to transfer them to a separate document (Perspectives of AI on Psychosocial Implications of Global Modelling, 2024). There the pattern of question/responses could be further developed under more appropriate section headings.

The AI facilities previously tested both offered the possibility of uploading relatively large PDF files to enable focused analysis. This suggested a different kind of test through uploading to each the PDF version of a single issue of an academic journal (as indicated below). The interaction recorded in what follows is a report of the process of question/resonse relating both to the issue as a whole and to particular contributions therein. In addition to a summary of the issue, the opportunity was taken (as before) to elicit the transformation of that summary into poetic form and into images (in the case of ChatGPT's DALL-E plugin).

Both AI faciliies were challenged with the possibility of generating musical representations of the themes evoked in the issue -- given the rapid development of applications with such facilities and the continuing research on sonification of data (Sonification as a mnemonic aid to global sensemaking, 2020). Whilst both engaged in an insightful speculative interaction about that possibility, and the requisite preliminary analysis, neither was able to offer directly any experimental musical rendering at this stage. The possibility elicited concluding symbolic implications of relevance to governance and interdisciplinarity.

As with the earlier exercises cited, the following exploration necessarily makes extensive use of AI. The role of such AI facilities as an "aggregator" of non-numeric information, rather than as a "computer" of numeric data was previously noted. Reservations regarding such use were also noted, both with regard to the questionable verbosity and style of responses, and what could be termed an undue degree of "algorithmic enthusiasm" for the relevance of the questions posed (Eliciting integrative insight via ChatGPT, 2024). Such enthusiasm could be readily caricatured as a form of "ingratiation" detracting from the responses. Other styles of presentation could have been requested of the AI facilities. A future technical possibility is to present the questions in a single document with links to the responses in separate documents.

Of particular interest however is any critical assessment of the extent to which the responses frame new insights rather than a preponderance of "strategic clichés" -- potentially derived from the reports of that quality which feature in many authoritative references. The intent is to "bear witness" to what is increasingly possible technically with any journal, even though the responses may be questionable. This applies particularly to the use of the image generation facility whose included results are primarily indicative of future possibilities rather than useful at this time.

As previously noted, a merit of this approach is that readers can explore alternative articulations by repeating (or amending) the questions to the AI facilities to which they have access -- especially as those facilities become more sophisticated and have a wider access to relevant published research. As with this experiment, this would involve uploading to other AI facility one (or more) PDF versions. As in the previous experiments, the responses of ChatGPT are distinctively presented below in grayed areas, in parallel with those of Claude 3.

As previously noted with such experiments, a particular concern is with the biases introduced in framing prompts -- readily challenged to the extent that they take the form of "leading questions". Although proposed to the editors of the journal, the opportunity of framing questions from their perspective did not evoke any response. The results presented cannot therefore be construed as reflecting their approval of the exercise in any way.


Overview of content and focus

Question: To the extent that the content reflects an extensively articulated world view, can you summarize the contents in a comment of appropriate scope

# Show/Hide AI response #

Question: How would you express the consensus implied by the contents, potentially in contrast to indications of disagreement

# Show/Hide AI response #

Question: In the light of the arguments of Terrence Deacon, how could you articulate what is "missing"

# Show/Hide AI response #

Challenge of authenticity in relation to spiritual intelligence

Question: The issue includes a contribution by Mark Vernon on AI and Spiritual Intelligence. Could you comment on the relation of artificial intelligence to spiritual intelligence -- in the light of the challenge of "human artifice" in misrepresentation of the spiritual. Given the Turing Test applied to AI, does this challenge call for a test of "authenticity" -- which some humans could well fail in promoting spirituality

# Show/Hide AI response #

Question: That response avoids the key issue of the ability of humans (without AI assistance) to employ "artifice" to represent spiritual insights. Correspondingly problematic will be the ability of AI to articulate spiritual insights in a manner deemed credible and insightful as a result of skilled access to sacred writings and the like. The current use by some priests to have sermons prepared by AI highlights the challenge. The question is then how is "artifice" to be distinguished from "artificial" in the presentation of spiritual insights

# Show/Hide AI response #

Question: To what extent do conventional appreciations of the "authentic" detract from the challenge of fruitful engagement with the "unauthentic" as an obvious (and much deprecated) feature of experiential reality. Can this be recognized as related to a more general challenge of the engagement with "ignorance" and the (naive) assumption that the "engager" is not characterized by both.

# Show/Hide AI response #

Question: In the light of that response, what are the implications for the authenticity of the experience of artificial intelligence -- or the lack thereof

# Show/Hide AI response #

Issues of dramatic global concern

Question: How does the focus of the contributions contribute to solving global physical problems such as climate change and biodiversity-loss?

# Show/Hide AI response #

Question: Are there detectable implications of a vital complementarity between the "inner" perspectives evoked and the "outer" issues of wider concern in society. If the outer perspectives are to be understood as issues of "misplaced concreteness", what might then be inferred as "misplaced" in the focus on inner perspectives

# Show/Hide AI response #

Question: As understood by physics, the more fundamental implications of "complementarity" follow from the Heisenberg Uncertainty Principle. How might an analogue -- or generalization -- be of relevance to the traditional challenge between "outer" and "inner" perspectives. In the case of the former, misplaced concreteness can be evoked. In the case of the latter is there a degree of failure of some form of experiential cognitive embodiment

# Show/Hide AI response #

Question: The journal issue includes a commentary by Peter Russell on The Curse of Exponential Growth, with its implictions for the future of humanity in the longer term. Could you comment on assumptions regarding the conceptual framing of "humanity" and the inference that -- however it is to be understood -- it may be faced with some form of "extinction"

# Show/Hide AI response #

Question: That response tends to confirm the existence of a degree of facile oversimplification in reference to "humanity" and "human" -- and by extension to "human values". This calls into question any corresponding understanding of "extinction" -- especially in the light of insights from fundamental physics of which analogies might prove to be relevant in a more general framework

# Show/Hide AI response #

Question: In the light of that response, how is "death" to be understood in the light of current speculations regarding quantum consciousness. Is this to be explored in relation to a reframing of "rebirth", "reincarnation" and "Renaissance"

# Show/Hide AI response #

Questions asked versus Answers offered

Question: Is it possible to identify (and list) specific questions asked by the contributions in contrast to their answers to questions that they themselves ask. To be clear, I am not interested in the answers provided but rather the questions formulated (in the expectation they may possibly be answered by others), namely the open questions. Does that simplify the task of a detailed review

# Show/Hide AI response #

Question: Are you able to detect any form of disagreement or incompatibility between contributions in the journal issue. How does this relate to appreciation of critical thinking

# Show/Hide AI response #

Facilitation of contributor dialogue by AI

Question: How might the dynamic and evolving dialogue implied by the contributions be fruitfully enabled and enhanced by AI -- in the foreseeable future

# Show/Hide AI response #

Question: That response is technically appropriate. The delicate issue seemingly avoided is how AI can facilitate dialogue where conventional facilitation techniques cannot be said to have been remarkably successful -- especially in handling fixed attitudes and biases

# Show/Hide AI response #

Indicative representation of insights in aesthetic forms

Question to ChatGPT: Recognizing that image-generation through DALL-E is still under active development, is it feasible to map the contents of that journal issue in a single image reflective of the contrasting perspectives represented. Accepting those constraints, as an indicative preliminary test, could you suggest a prompt to trigger such an image at this time

# Show/Hide AI response #

Question: Please go ahead with your suggested prompt.... Whilst I appreciate that result, a complete alternative would resemble more closely a system diagram, a thematic link map (of the contents), or even a "magic carpet". Could a prompt of that kind be presented to DALL-E

# Show/Hide AI response #

Question: Since this is an experiment, please start with what is most feasible

# Show/Hide AI response #

Question: Again, please proceed with what is most feasible

# Show/Hide AI response #

Question: Please elaborate on the thematic mapping as suggested

# Show/Hide AI response #

Question: Can you relate this to representation of a musical score -- reframing the bar chart visualization -- and suggesting how the issue as a whole might constitute a memorable melody or a symphony as a consequence of the interaction between the different voices [The Claude 3 analysis above was copied to ChatGPT to bypass the disruption of the interaction due to outage of OpenAI]

# Show/Hide AI response #

Question: The earlier exchange explored the possibility of a form of thematic sonification whereby themes in contributions were transformed into patterns of instrumental voices, tones or leitmotifs. To the ear this would then enable recognition of pattern repetition to a higher degree than in text presentations. Could you comment on what distinguishes boring repetition in music from interestingness and creativity -- especially given the implications for policy-related discourse

# Show/Hide AI response #

Question: That response avoids to some degree the implications for the issue in the case of academic and policy discourse. What constitutes boring repetition (in contrast to valued rehearsal of a familiar melody), when there may be a particular value associated with creativity and innovation (in contrast to what might be framed as uninteresting)

# Show/Hide AI response #

The relevance of the approach to a journal issue can also be examined in the light of the organization of the musical canon, as discussed separately (Reimagining the Canon to the Sounds of Cannon Fire, 2024).

Question: This is most appreciated. Could you comment further on the memorability enhanced by the musical leitmotifs. How might these relate to the complexity of a musical canon -- a framing argued by Douglas Hofstadter (Gödel, Escher, Bach, 1979)

# Show/Hide AI response #

Question: How could the approach you are articulating be adapted to the seemingly less complex configuration of the UN's 17 Sustainable Development Goals -- potentially with its 169 associated "tasks"

# Show/Hide AI response #

Question: You focused on several goals as an example. Can you extend the tentative musical attribution to the others. Could the goals be recognized in terms of voices or instruments, for example

# Show/Hide AI response #

Question: In symbolic terms, could you compare the outcome of such an endeavour with a cultural epic -- a contemporary equivalent of the Mahabharata or the Kalevala -- given the integrative significance these have offered

# Show/Hide AI response #

Question: Could you contrast that possibility with the worldwide enthusiasm engendered annually by the Eurovision Song Contest, given the musical values it promotes

# Show/Hide AI response #

Exceptional research is undertaken into the organization of tones from a cognitive perspective in terms of the Tonnetz (Tone-of-voice insights from music and the organization of the Tonnetz, 2020; Josh Walsh, Using Tonnetz Tone Mesh To Understand Jazz Harmony, Jazz Library, 27 April 2020)

Question: Adapting the metaphor otherwise, with the themes evoked understood as tones, could you comment on current research on the organization of tones in relation to the Tonnetz as suggesting insights into a more integrative and memorable organization of the common themes of governance -- taking appropriate account of principles of harmony and discord.

# Show/Hide AI response #

Question: Given the coherence of the topological mappings of the Tonnetz, with the limited array of tones (however they may be replicated in any periodic extension by octaves), could you speculate on how the SDGs might (for example) be configured as a Tonnetz of some particular topology

# Show/Hide AI response #

A framing in terms of tones, suggests recognition of a cognitive soundscape (Recognizing the challenge of soundscape comprehension in controversy and emergency, 2019; Landscape, soundscape, resonance: a place to be? 2019; Memescapes engendered and sustained by multidimensional soundscapes, 2014)

Potential symbolic implications of relevance to governance

Question: A speculative attribution of instruments to SDGs was offered. Arguably each SDG could be associated with a tone in a currently elusive cognitive soundcape. Beyond your examples, could you speculate further on how the array of SDGs could be understood as an array of tones -- potentially an array of complementaries from which some vital tones have been omitted.

# Show/Hide AI response #

Question: From a symbolic perspective, as evoked in folklore and mythology, there is a case for noting reference to iconic figures (especially deities) using music as a significant form of expression -- if not guidance. Could you cite examples of such archetypes and the instruments they used

# Show/Hide AI response #

Question: In the light of this exchange, and given the recognized mythological importance of the use of music, could you comment on the cognitive disconnect between themes evoked in academic journals (and governance more generally) and the organizaion of music -- especially given the manner in which music addresses challenges of harmony and discord, and distinctive "ways of looking"

# Show/Hide AI response #

Considerable importance is associated with anthems as offering an integrative focus for nations and cultures, exemplified by the use of Beethoven's composition as the Anthem of Europe -- as discussed separately (Reversing the Anthem of Europe to Signal Distress, 2016).

Question: Could you comment on how the extensive use of anthems, such as the Anthem of Europe (or the value associated with martial music), exemplifies that "cognitive disconnect" -- in that there is a virtually unrecognized correspondence between the much appreciated musical characteristics and the articulation and organization of strategic policies (typically alienating and unmemorable). How does this compare with the "connect" cultivated so assiduously in sacred music

# Show/Hide AI response #

Question: There is a curiously unquestionable appreciation of music (notably in the form of anthems) as being potentially a significant embodiment of cultural and institutional values -- especially with respect to strategic aspirations to a sense of harmony. That unquestioned appreciation distracts from the failure to determine how the musical articulation (in accordance with theories of harmony) "translates" into harmony in policy and strategic articulation -- especially in the face of opposition. Corresponding issues are evident in the case of sacred music and evocation of the "music of the spheres" by philosophers. Could you comment further on that form of cognitive disconnect and the failure to address it.

# Show/Hide AI response #

Question: The point that a composer brings together disparate voices and themes into a coherent whole indeed suggests that policymakers could strive to integrate diverse perspectives and interests into solutions that create a greater sense of social harmony. Seemingly missing is recognition of the very extensive development of the theory of harmony over centuries -- unmatched by any effort to draw on those insights in order to articulate policies of great subtlety and capable of transcending the binary oversimplification engendering violence. A corresponding pattern is evident in interdisciplnary discourse.

# Show/Hide AI response #

Question: Given the potential of music in enabling a higher degree of cognitive connectivity of relevance to governance and interdisciplinary discourse -- despite the conventional avoidance of that possibility (other than through varieties of tokenism) -- to what extent might the controversial proposals of Rupert Sheldrake (Morphic Resonance and Morphic Fields) indicate a means of moving forward.

# Show/Hide AI response #

Question: Given the limited success of mainstream methodologies in response to the challenges and crises of governance, whilst that response appropriately draws attention to the limited mainstream credibility of morphic resonance, could you comment on the contrast with the unquestioning gullibility with which anthems are conventionally appreciated and valued by authorities.

# Show/Hide AI response #

Question: How might the future exploration of the principles of designing a functional equivalent to an "anthem" be envisaged and enabled -- possibly with the aid of AI -- such as to embody cognitive connectivity of strategic relevance. Are there other forms complementary to "anthem"

# Show/Hide AI response #

Comment on technical constraints

Question: One part of the PDF test is whether you can handle a 5 MB issue of an academic journal in order to enable questions to be asked of it

# Show/Hide AI response #

As the following interactions make evident, the use of ChatGPT can be much less problematic than that of Claude 3. Potentially illustrative of difficulties, OpenAI (and therefore ChatGPT) featured a major outage in the midst of the experimental interaction reported above. This disrupted sessions, losing continuity and access to the PDF file (which had to be uploaded repeatedly).

Even in the case of a paid subscription, Claude 3 has a relatively complex method of calculating how much the facility has been used (in the light of the size of any uploaded file and the complexity of the questions asked). This results in an indication of how many messages may still be asked before the session is terminated -- and access to the PDF is lost. A distinction is made between the Sonnet model and the more sophisticated Opus model (used above). On forcing postponement of further use of the Opus model, the opportunity is offered to continue with the Sonnet model, however switching to that alternative results in loss of abilty to consult the uploaded PDF. There is the possibility that such consultation may be continued within the Opus model "when the clock is reset" (provided the PDF is uploaded again). There are other points of confusion, as noted in the following.

Question: The PDF having been uploaded, is it correct that you will only allow access to it through the current session -- to the extent that it remains active. Namely is there a time constraint in the event there are other questions of it

# Show/Hide AI response #

Question: The questions have focused on one issue of the journal only. Could you clarify whether a second issue could be uploaded to enable questions to be addressed to both, or comparisons to be explored between them

# Show/Hide AI response #

Clearly producers of journals in future, or their readers, will be able to upload many issues to enable their exploration from particular perspectives. This facility is already available in various forms, but is evolving so rapidly within changing marketing frameworks that it was not considered feasible to make use of it in this preliminary experiment.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

For further updates on this site, subscribe here