Pop in Perpetuity

Exactly a year ago, I blogged about ageing rockers and their propensity to continue touring and recording. This past weekend I experienced two events that provided almost polar opposites as to how musicians will perpetuate their “live” legacy. (Of course, in theory, their recordings will last forever, in physical, digital and streaming formats – as long as the equipment, technology and platforms survive…)

On the one hand, there was the Sun Ra Arkestra, who since their founder’s death in 1993, have continued to play the music of Sun Ra, respecting the sound, format and spirit of the original band formed in the 1950s. Some of the current band members played with Sun Ra himself, so there is a thread of continuity that connects us back to the past. But even as these surviving members depart this world, the music of Sun Ra will live on in concert form through subsequent generations of players. This type of perpetuity is not uncommon among bands of the 60s, 70s and 80s, although in many cases, there is usually at least one original band member performing, or members who overlapped with the band founders. (Some notable exceptions: Soft Machine, who continue performing and recording, but whose remaining original member left nearly 50 years ago; and Faust, who split into at least two separate bands that still tour and record under the same name.)

On the other hand, there was the high-tech concert presentation by the late composer and performer Ryuichi Sakamoto, entitled KAGAMI. This involved the use of AR headsets and a 3D avatar of Sakamoto, captured in sound and vision performing a selection of his music, sat at a grand piano. The audience, initially seated in a circle around the virtual performance area in order to acclimatise to what they were seeing, was invited to move around the avatar, and even peer into the open grand piano. Two things were striking: first, the 360 degree image was very impressive in the level of detail; second, even if someone was standing between the viewer and the avatar zone, the headset still presented the image of Sakamoto sat at the keyboard. The technology not only captures a digital visualisation of the pianist in action, it also replicates the notes he played as well as the tonal expression and the timbres, resonances and acoustics of the physical instrument. While the audio HiFi was superior to the atavistic CGI, the latter will no doubt improve; as will the slightly clunky and heavy headsets – the 50 minute duration is probably the most I could have endured.

Neither format of the above concerts is better or superior to the other. Both are authentic in their own way, and true to the artistry of musicians they celebrate. Of course, if we end up using AI to compose “new” music by Sakamoto, that may undermine that authenticity. But given Sun Ra’s origin story, I wouldn’t be surprised if he started beaming his new works from Saturn.

 

AI and Deep (and not so deep…) Fakes

The New York Times recently posted a quiz“can you tell the difference between a photograph, and an image created by AI?”

Of the quiz examples, a mix of actual photos and AI-generated content, I was only able to correctly identify 8/10 as to which were which. My significant other claimed to have scored 10/10! In my defence, I correctly identified all of the AI images, but I mistook two authentic photos as being fakes. Of the latter, one featured a bunch of famous people, most of whom I did not recognise, and the photo had been significantly cropped, removing much of the visual context (I also suspect it had been subject to some additional photo-shopping, given it was a publicity shot). The other real photo had been taken at such an unusual angle that it distorted some of the natural perspective, so as to make some elements look wonky. (But maybe I’ve become more cynical or sceptical, and therefore I tend to disbelieve more of what I see, the more I know I am being exposed to AI-generated content?)

How can we remain alert to AI deceptions, while at the same time recognizing and embracing the potential that this amazing technology has to offer?

Taking my lead from the New York Times article, the following blog has been created using ChatGPT. All I did was enter some brief subject headings (including the title), a series of internet links, and a prompt to turn it into a blog on AI and fakes. Can you tell what is true, what is hallucination, and what important information has been left out?

AI and Deep (and not so deep…) Fakes

Artificial Intelligence (AI) has revolutionized numerous sectors, bringing forth innovations that were once unimaginable. However, one of the more controversial applications of AI is in the creation of deep fakes. These are hyper-realistic digital falsifications created using AI, capable of mimicking real people’s appearances and voices. This technology has sparked debates over ethics, security, and the future of digital media. Let’s delve into some recent examples and the implications they bring.

Dylan and Rodin: A Fabricated Encounter

A striking example of AI’s capacity to blur reality is the supposed encounter between Bob Dylan and the sculptor Auguste Rodin. In an article on Substack by Dave Haslam, the scenario of Dylan visiting Rodin’s Parisian studio is meticulously crafted, yet it’s a fabrication made plausible by AI tools. This fake story exemplifies how AI can create convincingly realistic yet entirely fictional narratives, challenging our ability to discern truth from fiction.

AI in Indian Elections

AI’s role extends beyond entertainment into more critical areas such as political campaigns. In the 2024 Indian elections, AI-generated deep fakes have been used to spread misinformation and manipulate public opinion. An article by ABC News details how AI is disrupting electoral processes, raising concerns about the integrity of democratic systems.

Mozilla’s Campaign Against Misinformation

In response to the growing threat of AI-generated misinformation, organizations like Mozilla have launched campaigns to protect the integrity of elections. Mozilla’s efforts aim to hold platforms like WhatsApp accountable for the spread of fake news and deep fakes, urging them to implement stricter controls to safeguard democratic processes.

Celebrity Persona Rights

AI’s ability to replicate real people has also sparked legal disputes, particularly concerning persona rights. Scarlett Johansson’s recent dispute with OpenAI highlights these issues. Johansson’s concerns about her likeness being used without consent underscore the broader debate about the ethical use of AI. As noted by Scientific American, the conflict brings to light questions about how AI-generated content can respect individual rights and privacy.

Legislative Actions on Deep Fakes

Governments are beginning to take action against the misuse of AI-generated content. In Australia, new laws are being proposed to combat the creation and distribution of deep fake pornography and other harmful images. The Guardian reports on legislative efforts to protect individuals from the malicious use of AI, reflecting a growing recognition of the need for regulation.

AI and Copyright

The intersection of AI and copyright law is another area of intense debate. A lawsuit involving famous authors against OpenAI raises questions about how AI uses copyrighted material for training and whether the content it generates can itself be copyrighted. This legal battle, reported by ABC News and Reuters, could set important precedents for how intellectual property laws adapt to the age of AI.

Conclusion

As AI technology continues to advance, its applications in creating deep fakes present both opportunities and challenges. While it can be used creatively and constructively, it also poses significant risks to privacy, security, and the authenticity of information. The ongoing developments in legislation, ethical guidelines, and technological safeguards will be crucial in shaping the future landscape of AI-generated content.

So, did you spot the “deliberate” error(s)? And what information was missing? Answers will be posted later this week.

Next week: AI & Music

Whose side is AI on?

At the risk of coming across as some sort of Luddite, recent commentary on Artificial Intelligence suggests that it is only natural to have concerns and misgivings about its rapid development and widespread deployment. Of course, at its heart, it’s just another technology at our disposal – but by its very definition, generative AI is not passive, and is likely to impact all areas of our life, whether we invite it in or not.

Over the next few weeks, I will be discussing some non-technical themes relating to AI – creativity and AI, legal implications of AI, and form over substance when it comes to AI itself.

To start with, these are a few of the questions that I have been mulling over:

– Is AI working for us, as a tool that we control and manage?  Or is AI working with us, in a partnership of equals? Or, more likely, is AI working against us, in the sense that it is happening to us, whether we like it or not, let alone whether we are actually aware of it?

– Is AI being wielded by a bunch of tech bros, who feed it with all their own prejudices, unconscious bias and cognitive limitations?

– Who decides what the Large Language Models (LLMs) that power AI are trained on?

– How does AI get permission to create derived content from our own Intellectual Property? Even if our content is on the web, being “publicly available” is not the same as “in the public domain”

– Who is responsible for what AI publishes, and are AI agents accountable for their actions? In the event of false, incorrect, misleading or inappropriate content created by AI, how do we get to clarify the record, or seek a right of reply?

– Why are AI tools adding increased caveats? (“This is not financial advice, this is not to be relied on in a court of law, this is only based on information available as at a certain point in time, this is not a recommendation, etc.”) And is this only going to increase, as in the recent example of changes to Google’s AI-generated search results? (But really, do we need to be told that eating rocks or adding glue to pizza are bad ideas?)

– From my own experience, tools like Chat GPT return “deliberate” factual errors. Why? Is it to keep us on our toes (“Gotcha!”)? Is it to use our responses (or lack thereof) to train the model to be more accurate? Is it to underline the caveat emptor principle (“What, you relied on Otter to write your college essay? What were you thinking?”). Or is it to counter plagiarism (“You could only have got that false information from our AI engine”). If you think the latter is far-fetched, I refer you to the notion of “trap streets” in maps and directories.

– Should AI tools contain better attribution (sources and acknowledgments) in their results? Should they disclose the list of “ingredients” used (like food labelling?) Should they provide verifiable citations for their references? (It’s an idea that is gaining some attention.)

– Finally, the increased use of cloud-based services and crowd-sourced content (not just in AI tools) means that there is the potential for overreach when it comes to end user licensing agreements by ChatGPT, Otter, Adobe Firefly, Gemini, Midjourney etc. Only recently, Adobe had to clarify latest changes to their service agreement, in response to some social media criticism.

Next week: AI and the Human Factor

Victorian Tech Startup Week – Pitch Night

As part of the recent Victorian Tech Startup Week, Silicon Beach Melbourne and YBF Melbourne hosted the city’s first in-person pitch night for over a year (thanks to the 3 lock-downs we have had in that time). Compered by Karen Finch of Legally Yours, and supported by OVHcloud, the esteemed judges for the evening were Farley Blackman (YBF), Yian Ling Tan (OVHcloud) and David Hauser (Silicon Beach).

The usual Silicon Beach rules applied – Round One featured 90-second pitches from each founder (and no slide decks), from which the judges shortlisted 3 startups for Round Two. The Round One presentations in order of appearance were (as usual, website links are embedded in the names):

TwistedXeros.com

Using “emotional phase shifting to accelerate personal growth and transformation through Insight, Manifestation and Neuroscience”, the impetus for this startup came about from the founder’s own experience. Designed to help overcome certain mental health issues associated with anxiety, the founder claims his technique can help practitioners overcome events such as panic attacks within 6 seconds (as opposed to 600 seconds with traditional CBT methods). Had been accepted into the Founders’ Institute, then COVID came along.

The Leaf Protein Co.

There is a growing demand for plant-based foods, both as a source of sustainable protein, and in response to the increased prevalence of food-based allergies (e.g., gluten and soy). Add concerns about GMOs, unsustainable agriculture and climate change, the founder is looking to develop a scalable process for extracting specific types of leaf protein, including arid-climate plants and Australian natives such as saltbush to counter soil salination. Currently seeking funding to pay for a CSIRO pilot to scale the protein extraction.

E-Toy Library

Essentially a toy-lending app, that provides an end-to-end process (source, distribute, cleanse, circulate) via a subscription model. In trials, already secured 50 customers and over 100 subscribers. Estimates there is a $2.4bn toy market in Australia – but it wasn’t clear how much of this market the founders aim to capture.

Kido Paint

This app aims to bring childrens’ drawings to life, using AI/ML to scan a photo of the drawing, and convert it into an animated 3-D digital file that can be rendered within the app using augmented reality.

Thorium Data

Using the oft-heard tag line “data is the new oil”, this B2B solution is designed to help companies organise, manage and extract more value from their data. It does this by resolving issues of data inconsistency, privacy, risk and governance. It also derives and assigns numerical factors to to individual datasets to assess the “value” of this data, and uses indices to benchmark that value.

QuestionID

This product feels like a cross between a wiki for academic research papers, and an open text search tool to find answers within the wiki database. I know from experience that repositories of published research reports (especially refereed and peer reviewed papers) are highly structured and tagged, with the emphasis being on classification, authorship and citation. Often, you sort of need to know in advance the rough answer to the question you want to pose. Significant resources are already allocated to maintaining and commercialising these existing databases, so I’m not sure how QuestionID will deal with IP and other rights associated with these reference resources.

HiveKeepers

HiveKeepers is designed to support beekeepers by helping them to establish and maintain healthier hives, and enhance their own livelihoods at a time when the industry is facing numerous challenges. At its core is a smart phone app that monitors IoT sensors (temperature, weather, weight, motion, sound, etc.) attached to the hive itself. Over time, the data will enable predictive analytics. With the launch of its MVP, HiveKeepers has already attarcted 700 customers globally.

Round Two

The three finalists selected from Round One were KidoPaint, LeafProtein and HiveKeepers. Each founder made a longer pitch, and then answered questions from the judges:

Kido Paint – The Q&A discussion centred on the commercial model (B2B/C, gift cards, in-app vouchers), the file conversion process (turnaround time can be 24- 48 hours), options for scaling, and getting the right price pint for user prices. So it’s not an instant result (which may disappoint some impatient younger users), and the 3-D rendering and animation is somewhat limited to the imagination of the AI/ML algorithms used in the conversion process.

LeafProtein – There was a further discussion on the approach to producing sustainable and allergen free plant proteins. For example, the attraction of pereskia is two-fold – a higher protein ratio, and an arid climate plant. Also, the aim is to counter mono-culture and GMO crops. A D2C brand has been launched (using small-scale production processes), while the CSIRO project is to designed to scale protein extraction, as well as develop an emulsifier for use in the food industry.

HiveKeepers – The founder talked more about the need to address climatic and environmental impact on hives. Having benefited from support from the La Trobe University and SVG Thrive AgriFood accelerator programs, this startup is seeking funding for product development – current price point is $105 USD per smart hive per annum. While the industry is seeing a 2% growth in new hives, it is also suffering significant hive losses due to parasites and diseases.

The overall winner on the night was LeafProtein.

Next week: From R&D to P&L