Quote Of The Year

Timeless Quotes - Sadly The Late Paul Shetler - "Its not Your Health Record it's a Government Record Of Your Health Information"

or

H. L. Mencken - "For every complex problem there is an answer that is clear, simple, and wrong."

Tuesday, December 12, 2023

You Have To Love The Delusion The Government Pushes Regarding “Big Tech”

 

I really love the periodic chest thumping we get from our National Government regarding regulation of ‘Big Tech’! 

Federal government moves to shatter big tech’s dominance and ‘anti-competitive’ behaviour

By jared lynch

Technology Editor

5:56PM December 8, 2023

The Albanese government is moving to rein in so-called “big tech” as AI platforms are rapidly adopted across the economy, backing the competition watchdog’s pleas for tighter UK-style laws.

In a potential win for smaller firms, the federal government has agreed “in principle” to the Australian Competition and Consumer Commission’s proposals to stamp out “harmful” behaviour from the world’s top five tech companies.

This includes establishing mandatory codes of conduct designed to prevent anti-competitive conduct, which includes preferencing their own rather than rival app stores and services. The reforms also include strengthening unfair contract terms laws, and forcing digital platforms to shut down scams, fake reviews and harmful apps.

ACCC acting chair Catriona Lowe said the changes would ensure a “fairer and more transparent” system, particularly for small and medium-sized ­businesses.

“Companies like Google, Apple, Meta, Microsoft and Amazon supply services that most Australians use every day. These digital platforms are often unavoidable ‘gatekeepers’ between Australian businesses and consumers, giving them huge influence across the whole economy,” Ms Lowe said.

“By promoting competition in these markets, the reforms will also give consumers more choice, higher quality services, and fairer terms and conditions.”

The ACCC called for the changes as part of its five-year inquiry into the market power of the digital platforms. It has been providing reports every six months on the progress of the inquiry, which began in 2020.

The regulator has highlighted Britain as a potential model in an effort to force Apple and Google to open their app stores to more developers and competitors. Germany, Japan and the EU have also tightened regulations for digital platforms.

While Apple began preparing late last year to allow applications from outside its lucrative App Store to be downloaded onto iPhones and iPads, in response to new EU laws, Ms Lowe said changes in one jurisdiction rarely extended to another.

“It is critical that the Australian government works quickly to implement these reforms so that consumers and small businesses aren’t left behind,” she said.

The new regulatory regime would work alongside Australia’s existing competition laws. Each code would introduce targeted obligations to address the types of anti-competitive conduct most relevant to that service.

Anti-competitive conduct highlighted in the ACCC’s latest report includes self-preferencing, where platforms favour their own services in search results and app stores, and “tying” or forcing developers to use app stores’ in-app payment systems, which charge commissions of up to 30 per cent.

The ACCC also cited “unfair and arbitrary treatment” of smaller businesses that rely on the platforms to reach customers.

ACCC chair Gina Cass-Gottlieb criticised the “ecosystems” of digital platforms late last month, saying they locked in consumers and limited choices, while collecting vast amounts of data. She said the ACCC’s reforms would ensure technology benefited business and consumers.

“Consumers who use multiple products from a single digital platform may be forced to agree to unfavourable terms and conditions and/or accept unpalatable data collection practices due to a lack of suitable alternatives or because it is simply too inconvenient or costly to move out of that ecosystem,” she said.

“Our proposed reforms include a call for targeted consumer protections and service-specific codes to prevent anti-competitive conduct by particular designated digital platforms.”

Meta, which owns Facebook, said: “There is nothing inherent in digital ecosystem businesses that present greater risks of anti-competitive con­duct or consumer harm than in other sectors.”

Microsoft said the ACCC needed to continue its “market-specific analysis when considering firms’ expansion activities and conduct”, while Apple and Amazon said the expansion into smart devices was “relatively recent”. Google said there were consumer advantages from its products working well together.

More here:

https://www.theaustralian.com.au/business/federal-government-moves-to-shatter-big-techs-dominance-and-anticompetitive-behaviour/news-story/2fd675cd7a354645e47982a9b371f446

Surely this is just a game! Without the services provided by ‘big tech’ life would be hardly recognisable. All regulation will be mostly with the agreement of the regulated and the regulators know it!

My view is that ultimately we will get the services we are given where the tech majors have an interest in their provision and where there is some money to be made. The truth is that overall Australians are a profit centre for big tech, one way or another, and that we just have to play along wit the game of providing our data to get the services we want!

Sure we can opt out but it is not clear just how well that actually goes and whether many are prepared to put in the effort to get there. Most seem happy with the deal as it is presently constructed and simply could not be bothered to change!

If you have managed to detach yourself send me some snail mail – while that is still possible- and I will share your approach on the blog!

I reckon our national relationship with ‘big tech’ is almost the definition of symbiosis and I am not expecting change any time soon – despite the huffing and puffing!

David.

Sunday, December 10, 2023

I Wonder Just How Effectively Google Is Going To Be Able To Monetize AI?

         This appeared a few days ago:

     Google’s new AI chatbot beats  OpenAI, human experts in tests

John Davidson Columnist

Google has launched what it says is the most advanced artificial intelligence invented, Gemini, leapfrogging OpenAI in the race to render human brains redundant.

The “multimodal” AI, trained from the ground up to handle questions asked via a mix of audio, photos, video and text, outperformed every other AI including OpenAI’s GPT-4 model in 30 out of the 32 most popular industry benchmarks, Google officials claimed.

Google’s new AI, Gemini, answers questions asked using a mix of voice, video, photos and typed text. 

It was also the first AI to outperform human experts in a key benchmark known as the Massive Multitask Language Understanding (MMLU) test, Google said.

The most advanced version of the AI, known as Gemini Ultra, will not be available until next year, but an intermediate version known as Gemini Pro will begin to power Google’s free chatbot, Bard, as of Thursday, Google said.

The version of Bard powered by Gemini Ultra, known as Bard Advanced, might well be a paid-for service.

“We’ll explore what monetisation might look like, but we don’t have anything specific on that right now,” Sissie Hsiao, vice president in charge of Assistant and Bard at Google, said.

A third, cut-down version of the AI, Gemini Nano, will appear in Android phones starting with Google’s Pixel 8 Pro phone, to answer complex voice, video, photo and written questions on the phone itself, without the need for an internet connection.

In a video demonstration, Gemini identifies that the photo is homework, marks it, and explains the errors.  

In a global launch event, the company showed off Gemini Ultra performing a range of tasks which, until now, were generally reserved for humans.

In one pre-recorded demonstration, Gemini Ultra was shown a photo of a child’s physics homework, and was able to read it, mark it, and explain the maths and physics errors the child had made, going into levels of detail far beyond what most parents would be capable of.

In another demonstration, two objects were held up in front of a webcam – an orange and a fidget spinner – and the AI was able to identify them both and explain that citrus and the spinner had something in common: they both could be “calming”.

Eli Collins, the vice president in charge of product at Google DeepMind, which developed Gemini, said one of the main features of Gemini was it was less likely to “hallucinate” than other AIs.

“Improving the accuracy of responses was one of the core training objectives of the model. When we talk about getting a better score on these benchmarks, it’s often a result of improving Gemini’s ability to reason and to answer questions factually,” he said.

(And, indeed, the Google search engine does contain plenty of references to the “calming” effects of both citrus and fidget spinners.)

When the orange was replaced by a Rubik’s Cube, the AI identified they were both examples of toys that adults, as well as children, play with.

Coding edge

Google also showed off Gemini figuring out what a complex join-the-dots puzzle was depicting, before anyone even joined the dots (“This is a picture of a crab,” the AI pre-empted.) The AI watched as someone performed a simple sleight of hand with a ball and three cups, and correctly predicted the ball would be in the left cup.

More here:

https://www.afr.com/technology/google-s-new-ai-chatbot-beats-openai-human-experts-in-tests-20231206-p5epgr

I gave Bard a run with the question: “What is the best antibiotic for tonsillitis?”

The core part of the answer given was spot on I reckon:

“I'm not able to provide medical advice, so I can't tell you the best antibiotic for tonsillitis. However, I can share some information that may help you:

Most cases of tonsillitis are caused by viruses, not bacteria. Therefore, antibiotics are not usually effective. However, in some cases, tonsillitis can be caused by bacteria, such as group A streptococcus. In these cases, antibiotics can be helpful.” And so on!!!

Good disclaimer and then reasonable answer!

The question with all this really resolves around how these tools should be best used and how we can sensibly evaluate answers we are given – especially in domains where we are not expert

I found this response interesting: What is the likely outcome of the war between Israel and Hamas?

Answer: The conflict in Israel and Gaza is complex and changing rapidly. If you'd like up-to-date information try using Google Search.

My reaction: “bloody clever response!”

Frankly I reckon we are now in the situation where we can get a reasonable answer to most reasonable questions in less than a minute and I find that amazing,

As a second year med student this would have been really useful to study from!

What is the course of the vagus nerve in female humans?

Answer:

The vagus nerve, also known as the 10th cranial nerve, plays a crucial role in various bodily functions, including digestion, heart rate, and breathing. Its course is similar in both male and female humans, with some minor variations.

Here's a general overview of the vagus nerve's course:

Origins:

  • Starts in the brainstem, specifically the medulla oblongata.
  • Has two roots: a larger motor root and a smaller sensory root.

Path:

  • Exits the skull through the jugular foramen, along with other cranial nerves and blood vessels.
  • Descends through the neck, alongside the carotid arteries and jugular veins.
  • Enters the thorax and passes through the superior mediastinum.
  • Branches out in the thorax and abdomen, innervating various organs.

Branches and innervation:

  • Pharyngeal branches: Supply the muscles of the pharynx, responsible for swallowing.
  • Laryngeal branches: Control the muscles of the larynx, involved in voice production.
  • Cardiac branches: Regulate heart rate and rhythm.
  • Pulmonary branches: Innervate the lungs, contributing to breathing and airway reflexes.
  • Esophageal branches: Aid in esophageal peristalsis, the movement of food down the esophagus.
  • Celiac branches: Supply the stomach, intestines, pancreas, and liver, influencing digestion and nutrient absorption.

Minor variations in females:

  • Due to anatomical differences in the chest and abdomen, the specific course of the vagus nerve might show slight variations in females compared to males.
  • For example, the vagus nerve may pass closer to the reproductive organs in females.

Additional notes:

  • The vagus nerve is a complex structure with numerous branches and functions. This is a simplified overview of its course.
  • For a more detailed understanding, it's recommended to consult anatomy textbooks or consult with a healthcare professional.

Just a great answer and I admit as good as one might have hoped for!

I reckon I can now flog all my textbooks – and fast - while they are worth something!  Really books are now obsolete except for reading for pleasure away from screens etc.!

As for how Google makes money with all this, I have no idea!

David.

AusHealthIT Poll Number 726 – Results – 10 December, 2023.

Here are the results of the poll.

Do You Believe The myHealthRecord Has Improved Patient Engagement With, And Understanding Of, Their Health Information?

Yes                                                                                  1 (3%)

No                                                                                  35 (90%)

I Have No Idea                                                               3 (7%)

Total No. Of Votes: 39

A clear outcome with a huge majority feeling that the myHR has added pretty much zero to their engagement with their health information.

Any insights on the poll are welcome, as a comment, as usual!

A good number of votes. But also a very clear outcome! 

3 of 39 who answered the poll admitted to not being sure about the answer to the question!

Again, many, many thanks to all those very few who voted! 

David.

Friday, December 08, 2023

Some Are Wanting To Take A Careful Approach To AI And Where It Might Lead!

This appeared last week:

Ensure the advantages of AI outweigh the risks

Unprecedented productivity? Or a catastrophe in the making?

The management agenda of the risks associated to the procuring, developing and adoption of AI across the enterprise moves into the C-Suite.

Artificial Intelligence. AI. The two words that have more than quadrupled in search interest since the advent of ChatGPT. And we do not need to look far to see it included in business strategies or road maps alongside a promise of greater productivity.

Any productivity gains, however, are not free. They bring a breadth of new challenges unique to AI. These span from how businesses will use AI, new roles and employment impacts, and the speed to which AI is morphing. These impacts can be productivity on one hand, and on the other, the loss of workforce and trust.

Think of a cross between ChatGPT and Siri, let’s call them “Service Agents”. As Service Agents mature, they will augment or automate many of the activities of our current customer service workforce; directly translating into productivity gains.

But, as enticing as productivity gains are, and as the use of AI matures, we begin to ask questions such as “How can executives be certain that the AI’s responses align with how the organisation has chosen to engage with its customers?” and “How do businesses know the AI is operating within the guardrails that also govern the human workforce?”

As AI progresses, these questions move from simple questions to complex requirements of governance and risk management. Issues that board directors need to be across, that the C-Suite needs to understand and that the executive teams need to manage.

We have seen it before with cyber-security. Technology issues in businesses can be hard to grasp. The longer a company takes to get on top of issues, the more exposed it is.

AI can be even more difficult for executives to grasp. We typically observe a vast underestimation of the size and materiality of the business risks created by AI.

Not only is AI fast-changing but its self-learning and dynamically responsive nature – and what this means to business – is something that business has never had to deal with.

Self-learning. Think of that for a moment. How do executives and board members know that the self-learning capabilities of the AI technology that an inhouse data scientist has created continues to remain on track to deliver the objectives for which it was intended?

AI is so categorically different in the way it works that businesses must manage it as a “socio-technology” as opposed to a traditional software technology that is well understood. The “socio” refers to the impact it has on humans, the way it is developed, and the need for humans to interact and manage AI for productive engagement. All of this suggests a need for proactive risk management. Executives should consider a lens they are familiar with; portfolio risk management, balancing an integrated pool of potential benefits with a broad set of drivers for potential loss. Despite the familiarity of risk management practices, the breadth of AI risks far exceeds traditional business risk measures.

DSG.ai, an AI specialist firm, has assembled more than 100 distinct dimensions of AI risk (The AI Risk Ontology) for active governance, risk and compliance (GRC) management if AI is to be scaled sustainably. When adopted, it provides executive visibility across the full AI risk landscape with the adaptability to allow for continuous change as other forms of AI technology (for example Generative AI and Agents) mature.

Those who see the significance of these issues recognise they cannot wait for regulation and are beginning to stand up AI internal audit teams and implement specialised AI governance systems to constantly monitor AI risks and performance. Counterintuitively, AI risk management done well actually improves productivity and momentum, as opposed to slowing down innovation.

One company in the ASX 20 recently undertook a deeply specialised AI audit and uncovered a high degree of inherent risk but did not have the capability to manage and remediate in ways that meet recognised global standards.

This prevented the organisation from effectively identifying sudden shifts in performance and found that their risk exposure was actually far greater than what was understood. The lack of ability to monitor for incidents also meant that any AI errors are most likely to go undetected until an irreversible and visible impact on customers is recorded.

Board directors, the C-Suite and executives need to understand that effective AI risk management must not be left as the sole responsibility of technologists and those enamoured with the technology.

Just as we have seen the far-reaching impacts of cyber risk, AI needs to be addressed today instead of kicking the risk-shaped can down the road.

Dr Elan Sasson is CEO of DSG, a global AI company operating in Europe and APAC helping enterprise businesses manage AI at scale through a range of risk management solutions.

Here is the link:

https://www.theaustralian.com.au/business/technology/ensure-the-advantages-of-ai-outweigh-the-risks/news-story/39a93fc14726a54da496228de2f4b792

While there is more than a tinge of the sale motive about this, there are some reasonable points made tat are worth noting!

With so much hype around AI at present it is worth taking in a range of views to get a feel for what is actually going on.

Certainly caution is warranted at this point!

David.