Category Archives: discussion

Wrapping Up: Seeing Earth, Talking to the Geon

To wrap up this bespoke residency, now that our 6 months (part-time) has come to an end, I thought it would be helpful to cover a bunch of ideas and workflows we’ve established, some problems, and future directions to explore. There’s a lot to unpack, but I’ll try and be succinct – with a few digressions.

Here’s a video that covers the main points, which I expand upon in the text below.

During the course of this residency I’ve conducted lots of experiments and had a great dialogue with Chris about how to approach things, leading down some inspiring pathways for future work.

Philip Island Multispectral QGIS

2D visualisation

Initially we started off with looking at how to visualise hyperspectral and multispectral satellite data – and it turns to be pretty straight-forward using Python and some programming help using AI – a great way to develop ~explained~ code for libraries one may be unfamiliar with.

You need to know how to iterate and debug a program, work through some documentation, and the data can be accessed in complex file formats and transformed into usable images. This can be done in Juypiter notebooks, running locally in e.g. Anaconda, or remotely on Google Colab or NCRIS Cloudstor notebooks. Pretty straight-forward. These programming assistants will significantly improve over time and complex tasks will become even simpler to prompt.

HDF View File Data
ChatGPT 3.5 HDF Python advice

What the data captures is an entirely different matter – and hyperspectral data is a lot more complicated than multispectral data. I explored a raycasting volume system for that in UE, but that is beyond the remit of this wrap-up. There are lots of different ways to approach it – the question is which one is most useful. It’s a bit “chicken and egg.”

In concert, the question arises as to what one can infer from the data – which is in itself a huge field of scientific and engineering research. It’s not just a matter of applying some kind of GIS colour palette to spectral data – there’s whole fields of analytics that can be applied. These range from naïve naked-eye approaches, through quantitative and statistical analyses to fascinating work in deep learning .

What we have attempted to do is to move this data from the exclusive purview of the specialist to the generalist, from the desktop GIS system to the spatially-located mobile device where an observer may ~actually~ be in a moment in time, and to establish how a human-AI interaction might be established that can create dialogue, queries and observations about the data and their immediate environment.

3D+ Visualisation

Similar approaches can be undertaken in Python for creating 3D+ representations of data, using e.g.  MatPlotLib or VisPy (amongst many others).

For our purposes, Python scripts can run in Unreal Engine/ Omniverse platforms (as well as Unity) and become involved in the creation of geometry, textures, actors and a whole range of actions and narrative entities, Very interesting to see how this is opening up as a result of Virtual Production pipelines, upon which art/science projects can piggyback. This includes creating complex time series animations, physics simulations and volumetric rendering, including interactions with other toolsets used in scientific visualisation and creative industries workflows. Python is the lingua franca.


Cesium for Unreal has progressed a great deal. It is currently more stable and flexible than implementations for Omniverse or Unity. I surmise that this is because of the source-available nature of Unreal, as opposed to the closed-source model of the other platforms. Smart move by Epic. I hope it stays that way and becomes more open over time. Cesium is opensource, which is crucial to its flexibility and widespread adoption.

AI and ML

Of course, the elephant in the room is Artificial Intelligence and Machine Learning. It has been fascinating to watch this evolve over the past 6 months – a huge hype-cycle reminiscent of the Blockchain frenzy of the last few years – but at least blockchain was never represented as an ‘existential risk’ . Nevertheless, quantum blockchain technologies will, some day, become human-actor authentication and provenential authorities for lots of different types of data – it may become the only way to distinguish between ‘real’ and generative datasets.

AI  is the definitive enabling technology of our time. It present risks (not yet existential ones) and great opportunities. Like any powerful technology it must be treated with great circumspection and aligned with scientific and ethical interests for the benefit of ‘humanity’. It’s a mirror of humanity, and humanity is not all good. Artistic engagement can help explore and critique this new domain.


David Chalmer’s Reality+ (2022) stimulates  thoughts about the interfusion of world, data and intention, as does Jeff Malpas’ Place and Experience: A Philosophical Topography (2nd Ed. 2018) and Peter Otto’s Multiplying Worlds: Romanticism, Modernity and the Emergence of Virtual Reality (2011).

Apple’s Vision Pro is the latest technological offering in this long history of the intermediation of the self, panorama and place. And it is compelling – not because of the artificial gaze projected to the outside world (deixis to the other), but because of the disposal of controllers – that it can operate by coded hand-gesture alone. Its parts are not new, but the bringing together of systems is. It looks very interesting.

Yet the price of all ‘complete’ XR is total surveillance, even with a ‘secure enclave’: it’s still a head in a box, inherently panoptic and performative.

One wonders how long it will be before we all need to start wearing tinfoil hats to resist implanted thoughts or inception. Quite a long time, I expect, but not forever. Besides, the notion of implanted thoughts is epistemically ambiguous – often these are simply referred to as ‘culture’, ‘beliefs’ and ‘language’. It’s all quite problematic in the post-truth, post-human world of the Novacene. More to contemplate.

Some Practical Examples

In these naive and early days of AI XR, the world that is opening up is fascinating, as I hope the brief sketches above demonstrate. I think of them simply as sketches in exploring how XR will become continuous across mobile devices, HMDs/spectacles and desktop and large immersive screens. Each device format has its own affordances and content, interactions and UI/UX needs to be cognizant of that – lots of interesting design considerations. Natural interactions seem the most compelling, as the premise of ubiquitous/ambient computing is that it will disappear into the background and essentially become invisible – except for intermediation with the world via AI agents such as our idea of the Geon.

I hope you’ve found the material I’ve covered here as interesting, useful and thought provoking as I have! My sincere thanks to Prof. Chris Fluke, the SmartSat CRC and ANAT for facilitating this absorbing residency.  Lots to think about and lots of ideas for future work.

Safe and responsible AI in Australia: discussion paper

Illustration of Supporting responsible AI: discussion paper
Supporting responsible AI: discussion paper. SD/AI Image by Peter Morse

In case you have found it impossible to find via either the ABC news article or Industry and Science Minister Ed Husic’s  media release page, or via the website of the Government of Australia here’s the actual Safe and responsible AI in Australia discussion paper:

Submissions can be made until July 23rd 2023.

Alternative link to pdf:

and another:

Australia’s AI Action Plan

Analysis and Policy Observatory (APO or Australian Policy Online) – which looks like a credible resource as far as I can see (WHOIS)(Registrant)- has a bunch of useful policy documents on it – and it’s searchable!

Bit of a discovery failure from the Australian Government website. How would you know where to look? Clearly they need an AI assistant such as SwiftSage (something similar coming your way soon).


Ambient AI

A community of abstract digital minds

Ambient AI

It’s always problematic making predictions – especially in times of huge technosocial change and disruption. We are experiencing one now (though it may not seem so apparent in day-to-day life) – important aspects need to be identified, and how they will evolve and move forward over the next decade. There are going to be huge, transformational impacts over the immediate future and, especially, our children’s lifetimes.

The principle emergent technology to understand is definitively AI – nothing else comes close, because it is so all-encompassing. Large Language Models are springing up everywhere, with surprising competencies, many of them opensource [1][2][3] and suitable for training upon domain-specific knowledges [4] as well as general tasks.

Interesting approaches in prompt-engineering (PE), chain-of-thought reasoning (CoT), reflexion[5] and, fascinatingly, ‘role-playing’[6] using LLMs, also seem to be improving benchmark performance in concert with reinforcement learning with human feedback (RLHF) [7]:

Thinking of these emergent capabilities, in the context of the current AI arms-race, the issue of human-AI alignment  [8] [9] is of crucial regulatory importance:

Ultimately, to figure out what we really need to worry about, we need better AI literacy among the general public and especially policy-makers.  We need better transparency on how these large AI systems work, how they are trained, and how they are evaluated.  We need independent evaluation, rather than relying on the unreproducible, “just trust us” results in technical reports from companies that profit from these technologies. We need new approaches to the scientific understanding of such models and government support for such research.

Indeed, as some have argued, we need a “Manhattan Project of intense research” on AI’s abilities, limitations, trustworthiness, and interpretability, where the investigation and results are open to anyone.  [9]

Placing this in the context of existential threat, it is well worth absorbing this interview with Geoffrey Hinton in it’s entirety:

Monoliths vs iOT

Although the above concerns sound like science fiction, they are not, and the consequence is that anyone working with AI development (which basically means anyone who interacts with AI systems) must situate themselves within an ethical discourse about consequences that may arise from the use of this technology.

Of course, we have all been doing this for many years through social media and recommender systems – like Amazon, Facebook, VK, Weibo , Pinterest, Etsy – and Google, MicrosoftApple, Netflix, Tesla, Uber, AirBnB etc. – and the millions of data-mining subsidiary industries that have built up around these. Subsidiary re-brands, data-farms, click-farms, bots, credit agencies, an endless web of information with trillions of connections.

In reference to Derrida, I might whimsically call this ‘n-Grammatology”  – given that the pursuit of n-grams has arrived us at this point for the ambiguous machines [10]. A point where the ostensive factivity of science meets the ambiguous epistemology and hermeneutics of embeddings in a vector space – the ‘black box’.

What we know is that AI is a ‘black box’ and that our minds are a ‘black box’, but we have little idea of how similar those ignorances are. They will perhaps be defined by counter-factuals, by what they are not.


One of the mythologies that surrounds AI that is hard to avoid is that it occurs ‘somewhere else’ on giant machines run by megacorporations or imaginary aliens:

However, as the interview with Hinton above indicates, what has been achieved is an incredible level of compression : a 1-trillion parameter LLM is about 1 terabyte in size:

What this seems to imply is that the kernel will easily fit onto mobile, edge-compute and iOT devices in the near future (e.g. Jetson Nano), and that these devices will probably be able to run independent multimodal AIs.

“AI” is essentially a kind of substrate-independent non-human intelligence, intrinsically capable of global reproduction across billions of devices. It is hard to see how it will not proliferate (with human assistance, initially) into this vast range of technical devices and become universally distributed, rather than existing solely as a service delivered online via APIs controlled by corporations and governments.

AI ‘Society’

The future of AI is not some kind of Colossus, but rather a kind of of global community of ambient interacting agents – a society. Like any society it will be complex, political and ideological – and throw parties:

Exactly how humans fit into this picture will require some careful consideration. Whether the existential risks come to pass are out of the control of most people, by definition. We will essentially be witnesses to the process, with very little opportunity to affect the direction in which it goes in the context of competition between state and corporate actors.

The moment when a human-level AGI emerges will be a singular historic rupture. It seems only a matter of time, an alarmingly short one.

For the next post I will put aside these speculative concerns, and detail some of the steps we have made towards developing a system that incorporates AI, ambient XR and Earth observation. My hope is that this will make some small contribution to a useful and ethical application of the technology.



[1] “Open Assistant.” Accessed May 9, 2023.

[2] “LLMs (LLMs),” May 6, 2023.

[3] “Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs.” Accessed May 9, 2023.

[4] philschmid blog. “How to Scale LLM Workloads to 20B+ with Amazon SageMaker Using Hugging Face and PyTorch FSDP,” May 2, 2023.

[5] Shinn, Noah, Beck Labash, and Ashwin Gopinath. “Reflexion: An Autonomous Agent with Dynamic Memory and Self-Reflection.” arXiv, March 20, 2023.

[6] Drexler, Eric. “Role Architectures: Applying LLMs to Consequential Tasks.” Accessed May 9, 2023.

[7] “Reinforcement Learning from Human Feedback.” In Wikipedia, March 30, 2023.

[8] Bengio, Yoshua . “Slowing down Development of AI Systems Passing the Turing Test.” Yoshua Bengio (blog), April 5, 2023.

[9] Mitchell, Melanie. “Thoughts on a Crazy Week in AI News.” Substack newsletter. AI: A Guide for Thinking Humans (blog), April 4, 2023.

[10] Singh, V., 2015. Ambiguity Machines: An Examination [WWW Document]. URL (accessed 4.26.23).

ChatGPT Perspectives

Interior life. Stable Diffusion image. Credit: Peter Morse

This post is a more general discussion about ChatGPT and related systems – it’s important to cut through the hype surrounding LLMs and absorb the sober scientific and cultural perspectives and questions around these systems and their capabilities. The impacts of these systems for knowledge work and creative work is going to be huge in the near future – so time to start understanding their context and implications.

S. Wolfram : What Is ChatGPT Doing … and Why Does It Work?

This is an excellent technical discussion about how Neural Nets (NNs) work, with interesting questions about the internal ‘black box’ goings-on – that are in general quite inscrutable. Wolfram is arguing for a rigorous scientific understanding of NNs, as they seem principally to have arisen as engineering exercises – things that work, but no-one really understands exactly why (‘lore’ in Wolfram’s estimation). This is a sharp counterpoint to the feuilleton hype about AI (which is, really, ‘Machine Learning’, or ‘Machine Representation’, as it is not ‘truly’ intelligent or aware). He makes interesting points about interfacing something like ChatGPT with Wolfram Alpha, which is a kind of computational knowledge engine, and argues convincingly that an interface between the two systems could solve many of the factual errors confabulated by the LLM, and provide something much more powerful in combination: a system that is ‘factually’ connected to the ‘world’ – and perhaps even capable of causal inference as a result.

The discussion touches upon several interesting philosophical/theoretical areas concerning the construction and emergence of language and discourse.

Human language—and the processes of thinking involved in generating it—have always seemed to represent a kind of pinnacle of complexity. And indeed it’s seemed somewhat remarkable that human brains—with their network of a “mere” 100 billion or so neurons (and maybe 100 trillion connections) could be responsible for it. Perhaps, one might have imagined, there’s something more to brains than their networks of neurons—like some new layer of undiscovered physics. But now with ChatGPT we’ve got an important new piece of information: we know that a pure, artificial neural network with about as many connections as brains have neurons is capable of doing a surprisingly good job of generating human language. (Wolfram, 2023)

Of great interest to me is the possibility of what one might call ’empirical semiotics’ or ‘computational semiotics’ – where semiotic generation and analysis (semiosis) could be underpinned by computational forms of emergence, categorisation and logic.

The success of ChatGPT is, I think, giving us evidence of a fundamental and important piece of science: it’s suggesting that we can expect there to be major new “laws of language”—and effectively “laws of thought”—out there to discover. In ChatGPT—built as it is as a neural net—those laws are at best implicit. But if we could somehow make the laws explicit, there’s the potential to do the kinds of things ChatGPT does in vastly more direct, efficient—and transparent—ways. (Wolfram, 2023)

Presumably many of these ‘laws’ are already uncovered or at least hinted-at by research in NLP and computational language models – but it appears very much a contentious field – especially with regard to what any formulation of what ‘intelligence’ is.

If there is one constant in the field of artificial intelligence it is exaggeration: There is always breathless hype and scornful naysaying. It is helpful to occasionally take stock of where we stand. (Browning & LeCun, 2022b)

To me it seems important to understand LLM cognates and extensions in multimodal systems – that intelligent systems can draw inferences across visual, audial, somatic and other sensory modalities beyond the textual and linguistic (Browning & LeCun, 2022a).

The underlying problem isn’t the AI. The problem is the limited nature of language. Once we abandon old assumptions about the connection between thought and language, it is clear that these systems are doomed to a shallow understanding that will never approximate the full-bodied thinking we see in humans. In short, despite being among the most impressive AI systems on the planet, these AI systems will never be much like us.(Browning & LeCun, 2022a).

The field of semiotics has a significant body of work covering these differing/interdependent signifying regimes – but not a great deal that is computationally reducible, as it has been more in the form of ‘literary criticism’ or humanities ‘theory’ (including in my own research background). This is clearly inadequate for a scientific approach as it is far too qualitative – more ‘top down’ than ‘bottom up’ – reminiscent of debates concerning symbolic reasoning vs (what might be termed) ’emergent’ reasoning.  However, there are examples in the work of C.S. Peirce, M.A.K. Halliday and others that may be useful for thinking about this domain. In the area of cognitive neuroscience/neuroanthropology I immediately think of the work of T. Deacon, A. DamasioD. DeutschJ. Hawkins and others that synthesise this inter-disciplinary domain of knowledge into useful ways of thinking about what might constitute an intelligent system and how it might emerge.

For non-specialists like me there is much to absorb – that can inform ways of critically engaging with this novel technology.

It is terribly important to not be naive about this stuff (AI), as it will (and has already) have transformational impacts upon personhood, economic, political and natural systems, for good and for bad. It is hard to imagine a future when a self-aware, agentive  machine intelligence is more than a science ‘fiction.’ It sounds absurd, but perhaps it isn’t.

Imagine a world where people’s online images, text, music, voice recordings, videos, and code get gathered largely without consent to train AI models, and sold back to them for $10 a month. We’re already there but imagine something beyond that – and assume it’s incredible…

…Here’s a thought experiment: imagine an AGI system that advises taxing billionaires at a rate of 95 percent and redistributing their wealth for the benefit of humanity. Will it ever be hooked into the banking system to effect its recommended changes? No, it will not. Will those minding the AGI actually carry out those orders? Again, no.

No one with wealth and power is going to cede authority to software, or allow it to take away even some of their wealth and power, no matter how “smart” it is. No VIP wants AGI dictating their diminishment. And any AGI that gives primarily the powerful and wealthy more power and wealth, or maintains the status quo, is not quite what we’d describe as a technology that, as OpenAI puts it, benefits all of humanity. (Claburn, T. , The Inquirer, 2023)

We don’t have a good definition of intelligence – so it seems best to define it operationally (as Friston et. al. 2022 does). At this stage the take-away is that LLM’s are clearly what the label says: they are language models, not artificial intelligences – they are, literally, Rhetorical Devices.

LLMs statistically parameterise a huge amount of ‘knowledge’ about linguistic representations of the world – based upon their massive set of ‘training’ data. These terms are information, signs, similes, metaphors, metonyms, synedoches –  abstractions that can exhibit indefiniteness: degrees of epistemic and ontic undecidability or infinite regression. Uncertainty.

LLMs seem to respond dialogically, perhaps following chains of reasoning akin to the vectors in ‘meaning space’ that Wolfram discusses (’embeddings’  – examples of t-SNE or word2vec dimensional reduction plots). These dialogues can also be guided by user interaction via the Chatbot query interface through ‘chain-of-thought’ reasoning – which demonstrably improves the model performance (even, it seems, when the model performs what might be the equivalent of ‘self-talk’).

Larger models seem to improve inferential reasoning – yet presumably there will be drawbacks or limits in a scale-only approach. Not least amongst these being the prodigious amounts of compute required, and their concomitant use of electricity and consequent carbon-impacts.

Are they ’emulations’ or ‘simulations’? What would this distinction imply?*** To me, it indicates that it (an LLM) is a map, not an actor; a palimpsest, not an agent.

A counterpoint.

At no point with chatGPT is there any self-initiation. Purpose and curiosity, at this juncture, seem very much a human property. Whether this will continue to be the case, time will tell.


Graph explaining Dunning-Kruger curve, reinterpreted for ChatGPT.
Credit: Maurizio Bisogni


For our current purposes we can be reasonably confident about the ongoing necessity of the ‘human-in-the-loop’ approach we’re pursuing. For the time being. And with which humans?



*ChatGPT apparently implements this type of response training interface – thumbs-up/thumbs-down.

***Thanks to my colleague P. Bourke for drawing this distinction to my attention.


Altman, S., n.d. Planning for AGI and beyond [WWW Document]. OpenAI. URL (accessed 3.10.23).

Ananthaswamy, A., 2023. In AI, is bigger always better? Nature 615, 202–205.

Browning, Jacob, and Yann LeCun. “What AI Can Tell Us About Intelligence,” June 16, 2022.

Browning, Jacob. “AI And The Limits Of Language,” August 23, 2022.

Claburn, T., n.d. OpenAI CEO heralds AGI no one in their right mind would want [WWW Document]. URL (accessed 3.10.23).

Daull, Xavier, Patrice Bellot, Emmanuel Bruno, Vincent Martin, and Elisabeth Murisasco. “Complex QA and Language Models Hybrid Architectures, Survey.” arXiv, February 17, 2023.

Deacon, Terrence W. Incomplete Nature: How Mind Emerged from Matter. WW Norton & Company, 2011.Deacon, Terrence W. The Symbolic Species: The Co-Evolution of Language and the Brain. WW Norton & Company, 1998. ISBN:9780393049916

Dennett, D.C. Consciousness Explained. Little, Brown, 2017. ISBN: 0-316-18065-3

Deutsch, David. The Beginning of Infinity: Explanations That Transform The World. Penguin UK, 2011. ISBN: 9780140278163

Friston, Karl J, Maxwell J D Ramstead, Alex B Kiefer, Alexander Tschantz, Christopher L Buckley, Mahault Albarracin, Riddhi J Pitliya, et al. “Designing Ecosystems of Intelligence from First Principles,” December 2022.

Halliday, Michael Alexander Kirkwood. Language as Social Semiotic. London Arnold, 1978. ISBN:9780713159677

Hawkins, Jeff. A Thousand Brains: A New Theory of Intelligence. Hachette UK, 2021.

Huang, Jiaxin, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. “Large Language Models Can Self-Improve.” arXiv, October 25, 2022.

Ouyang, Long, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, et al. “Training Language Models to Follow Instructions with Human Feedback.” arXiv, March 4, 2022.

Pearl, J., Mackenzie, D., 2018. The Book of Why: The New Science of Cause and Effect. Penguin UK. ISBN: 9780141982410

Savage, N., 2023. Why artificial intelligence needs to understand consequences. Nature.

Tanaka-Ishii, K., 2010. Semiotics of Programming. Cambridge University Press. ISBN:9780521516556

Tenachi, W., Ibata, R., Diakogiannis, F.I., 2023. Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws.

Massimini, M., Tononi, G., 2018. Sizing Up Consciousness: Towards an Objective Measure of the Capacity for Experience. Oxford University Press. ISBN:9780198728443

Wolfram, Stephen. “What Is ChatGPT Doing … and Why Does It Work?,” February 14, 2023.

Mirror, Mirror on the Wall: Working with AI

Mirror, mirror on the wall – imaged generated by Stable Diffusion. Image credit: Peter Morse

It’s important when working with the current generation of AI systems (principally Large Language Models or LLMs) to approach them with caution and circumspection. The reason for this is essentially human fallibility – both by the end-user and by the system itself.

The computer science behind generative AI is moving so fast that innovations emerge every month. How researchers choose to use them will dictate their, and our, future.

(Stokel-Walker and Van Noorden, 2023: 214-16)

The system I’m currently using – ChatGPT – is genuinely revolutionary in terms of how helpful it is for programming assistance – it has saved me hours and hours of time working out some approaches I can develop to programming problems. The underpinning technology is, in fact, several years old, but the way it has been implemented and its availability is what sets it apart (expect many more of these sorts of systems over the next few years).

But it has also hallucinated things that simply don’t exist – and presented them in a convincing matter-of-fact way:

Q: How can I import a multispectral geotiff into Unreal Engine 5 and break it into different layers for selected wavebands all correctly geolocated?

ChatGPT: To import a multispectral GeoTIFF into Unreal Engine 5 and break it into different layers for selected wavebands, you will need to use a plugin or script that is capable of handling multispectral imagery. One example is the “GeoTIFF Import” plugin, which is available on the Unreal Engine Marketplace. This plugin allows you to import a GeoTIFF file and separate it into different layers for each band.

Once you’ve imported the GeoTIFF, you can use the “Landscape” tool to create a terrain that corresponds to the image. You can then use the “Landscape Layer Blend” node in the material editor to control the blending between the different layers of the image.

To correctly geolocate the image, you will need to use the “World Aligned Blocking” feature, which allows you to align the image with the terrain using GPS coordinates. In the Unreal Engine, you can use the “World Settings” panel to set the GPS coordinates for your image.

Alternatively, you can use Python scripts that are designed to handle the import of multispectral GeoTIFFs and separate them into different layers, such as rasterio and gdal libraries. You can then use these layers as textures in the Unreal Engine to create a 3D representation of the multispectral data with accurate geolocation.

I’ve highlighted the plausible falsehoods – for instance, there is no GeoTIFF import plugin for Unreal Engine in the UE Marketplace. There are off-the-shelf solutions for this such as Landscaping, Cesium and Terraform Pro (amongst others out there on the interwebs) – and it would be great if UE could directly import GeoTIFFs via a native plugin.  But there isn’t – instead ChatGPT hallucinates a solution. It sounds plausible – just like using a ‘World Aligned Blocking’ feature, or simply using the ‘World Settings’ panel to set GPS coordinates.

Essentially the system is confabulating. Large Language Models are pejoratively referred to as ‘stochastic parrots’ – they act basically as ‘token prediction’ machines, where there is no awareness of on-going context within a given text generated by the system, and certainly no concept of inference or common-sense. Long passages of text or programming are simply realisations of the likelihood of these generated token streams on a larger scale than  individual words**, articulated within the interpretive reception of the ‘user’ that may perceive ‘seeming’ coherence:

We say seemingly coherent because coherence is in fact in the eye of the beholder. Our human understanding of coherence derives from our ability to recognize interlocutors’ beliefs [30, 31] and intentions [23, 33] within context [32]. That is, human language use takes place between individuals who share common ground and are mutually aware of that sharing (and its extent), who have communicative intents which they use language to convey, and who model each others’ mental states as they communicate. As such, human communication relies on the interpretation of implicit meaning conveyed between individuals….

Text generated by an LM is not grounded in communicative intent, any model of the world, or any model of the reader’s state of mind. It can’t have been, because the training data never included sharing thoughts with a listener, nor does the machine have the ability to do that. This can seem counter-intuitive given the increasingly fluent qualities of automatically generated text, but we have to account for the fact that our perception of natural language text, regardless of how it was generated, is mediated by our own linguistic competence and our predisposition to interpret communicative acts as conveying coherent meaning and intent, whether or not they do [89, 140]. The problem is, if one side of the communication does not have meaning, then the comprehension of the implicit meaning is an illusion arising from our singular human understanding of language (independent of the model).

(Bender and Gebru, 2021:616)

Nevertheless, even with these caveats, the system provides a valuable and useful distillation of a hugely broad-range of knowledge, and can present it to the end user in an actionable way. This has been demonstrated by my use of it in exploring approaches toward Python programming for the manipulation of GIS data. It has been a kind of dialogue – as it has provided useful suggestions, clarified the steps taken in the programming examples it has supplied, and helped me correct processes that do not work.

But it is not a dialogue with an agent – seeming more akin to a revealing mirror, or a complex echo, from which I can bounce back and forth ideas, attempting to discern a truth for my questions. This brings with it a variety of risks, depending upon the context and domain in which it is applied:

The fundamental problem is that GPT-3 learned about language from the Internet: Its massive training dataset included not just news articles, Wikipedia entries, and online books, but also every unsavory discussion on Reddit and other sites. From that morass of verbiage—both upstanding and unsavory—it drew 175 billion parameters that define its language. As Prabhu puts it: “These things it’s saying, they’re not coming out of a vacuum. It’s holding up a mirror.” Whatever GPT-3’s failings, it learned them from humans.
Moving beyond this current state, the path to ‘true’ AI, human-level AI, AGI (Artificial General Intelligence) and ASI (Artificial Super-Intelligence), may be shortish (20 years) or longish (50 years) – but given the current pace of development, my impression is that it will be measured in decades, not centuries. Domain experts have already mapped out research programs that encompass many of the conceptual and scientific breakthroughs that need to be made for this to occur (Hutter, 2005; LeCun, 2022), neatly adumbrated by Friston et al. (2022):
Academic research as well as popular media often depict both AGI and ASI as singular and monolithic AI systems, akin to super-intelligent, human individuals. However, intelligence is ubiquitous in natural systems—and generally looks very different from this. Physically complex, expressive systems, such as human beings, are uniquely capable of feats like explicit symbolic communication or mathematical reasoning. But these paradigmatic manifestations of intelligence exist along with, and emerge from, many simpler forms of intelligence found throughout the animal kingdom, as well as less overt forms of intelligence that pervade nature. (p.4)
…AGI and ASI will emerge from the interaction of intelligences networked into a hyper-spatial web or ecosystem of natural and artificial intelligence. We have proposed active inference as a technology uniquely suited to the collaborative design of an ecosystem of natural and synthetic sensemaking, in which humans are integral participants—what we call shared intelligence. The Bayesian mechanics of intelligent systems that follows from active inference led us to define intelligence operationally, as the accumulation of evidence for an agent’s generative model of their sensed world—also known as self-evidencing. (p.19)
In the meantime, it is the role of the human interlocutor to establish the inferential framework with which we work with these systems. It is remarkable that what until recently seemed like science-fictional concepts are now available for use.
A critical awareness of machine learning and machine intelligence capabilities seems to me to be a prudent mindset to develop for any engagement with technology that interfaces with Earth observation systems – indeed, any observational system, because it is up to us human beings to develop frameworks for designing goals for these systems, and developing the capacity to interrogate and understand them in accessible ways, discern objective and/or consensual truth and to deploy them for good.
For argument’s sake – here’s some hallucinated images of bushfires taken from a satellite, created using Stable Diffusion 1.5. Who’s to say they aren’t real images of real places? How would you be able to tell?
Fake Satellite I
Fake Satellite II
Fake Satellite III
Fake Satellite IV
Fake Satellite V
Fake Satellite VI
**This is a supposition I have made that may or may not be correct (I don’t know, so I am rephrasing this/correcting this as my knowledge increases). Tokens are word fragments or components, and, apparently (see next posts) each is added singly on a stochastic basis – but presumably the probabilistic value is informed by larger-scale probabilistic structures than individual words in sequence. There must be syntagmatic and paradigmatic values at play.

Bender, Emily M., Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell. “On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜.” In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–23. Virtual Event Canada: ACM, 2021.
Friston, Karl J, Maxwell J D Ramstead, Alex B Kiefer, Alexander Tschantz, Christopher L Buckley, Mahault Albarracin, Riddhi J Pitliya, et al. “Designing Ecosystems of Intelligence from First Principles,” December 2022.
Hutter, Marcus. Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Germany: Springer, 2005.
LeCun, Yann. “A Path Towards Autonomous Machine Intelligence Version 0.9.2, 2022-06-27,” July 2022.
Stokel-Walker, Chris, and Richard Van Noorden. “What ChatGPT and Generative AI Mean for Science.” Nature 614, no. 7947 (February 6, 2023): 214–16.
Strickland, Eliza. “OpenAI’s GPT-3 Speaks! (Kindly Disregard Toxic Language).” Accessed February 7, 2023.

Technical Webinar: Can satellites monitor crop and pasture quality across Australia?

From the SmartSat CRC Newsletter:

This Technical Presentation hosted by Ha Thanh Nguyen, Research Scientist in Digital Interactions (Agriculture & Food) at CSIRO explores the outcomes of SmartSat Project P3.25: Can satellites monitor crop and pasture quality across Australia?

Knowledge of crop and pasture quality can provide the industry with insights to assist with the grazing management of pastures and input management decisions for crops. Handheld and lab-based spectroscopy have been extensively employed to monitor quality-based plant attributes. The methods employed are time consuming and expensive to implement and do not provide the industry with insights into the temporal trends of the critical variables. High resolution and frequent return time can overcome numerous deficiencies affecting equivalent visible IR and SWIR platforms, that limit the ability to create a viable product around crop and pasture quality. This project conducted a feasibility analysis capitalising on existing and planned satellite missions, including the Aquawatch satellites and precursors to test development of new high frequency products for crop and pasture quality across the Australian landscape. This project is led by Dr Roger Lawes, Principal Research Scientist at CSIRO Agriculture Flagship and includes participants from CSIRO and the Grains Research and Development Corporation. For more information visit…