Andrew Eborn Back to The Futurist / AE on AI
There have been seismic developments in the world of AI, Robotics & Tech.
- ChatGPT has reached 100 million users in just 2 months
- Love by AI Moonpig is looking to integrate ChatGPT to help tongue tied lovers
- AI may help the development of new drugs – collaboration between University of Sheffield and AstraZeneca
- Google has developed AI system SingSong to generate musical backing track
- Scientists working to bring back the Dodo
- Deep Fake recordings of Emma Watson reading Mein Kampf
- By 2030 Amazon will have more robots than human employees
The AI chatbot has already caught the attention of Moonpig, which is exploring the possibility of integrating ChatGPT into its own systems to help lovers communicate more effectively.
Meanwhile, Google has developed an AI system called SingSong that can generate a musical backing track to accompany a person’s recorded singing. By using an algorithm to separate the instrumental and vocal parts from 46,000 hours of music, SingSong creates the appropriate rhythm, key, and harmonies to accompany a singer’s voice.
In the world of medicine, a new development may help speed up the discovery of new drugs. Researchers at the University of Sheffield and AstraZeneca have collaborated to create an AI system that can predict whether a new drug candidate will interact with the right protein molecules in the human body to fight disease. The AI, called DrugBAN, is trained to understand the substructures of proteins and drugs and how they interact with each other, which it draws on to make predictions about how new drugs will behave. In the next stage of development, the team plans to use more in-depth data to make the AI even more accurate.
ChatGPT reaches 100 million users two months after launch
Unprecedented take-up may make AI chatbot the fastest-growing consumer internet app ever, analysts say
It had about 590m visits in January from 100 million unique visitors, according to analysis by data firm Similarweb. Analysts at investment bank UBS said the rate of growth was unprecedented for a consumer app.
By comparison it took TikTok about nine months to reach 100 million users and Instagram more than two years, according to data from Sensor Tower, an app analysis firm.
ChatGPT can generate articles, essays, jokes, poetry and job applications in response to text prompts. OpenAI, a private company backed by Microsoft, made it available to the public for free in late November.
OpenAI also developed the AI-powered image generator Dall-E and is at the forefront of generative AI, or technology trained on vast amounts of text and images that can create content from a simple text prompt.
This week OpenAI announced a $20 monthly subscription, initially only for users in the United States. It would provide a more stable and faster service as well as the opportunity to try new features first, the company said.
Last month, Microsoft announced another multibillion-dollar investment in OpenAI in the form of cash and provision of cloud computing. On Wednesday Microsoft launched a premium version of its Teams product backed by ChatGPT, offering AI-powered extras such as automatically generated meeting notes. The tool also divides recaps of meetings into sections, based on the meeting transcript.
Love by AI
Moonpig looking into integrating ChatGPT into its systems to help tongue tied lovers
Google AI generates musical backing tracks to accompany singers
An artificial intelligence called SingSong can take a recording of a person singing and create a backing track for it with the appropriate rhythm, key and harmonies. To develop it, Jesse Engel and his colleagues at Google Research used an algorithm to separate the instrumental and vocal parts from 46,000 hours of music and then fine-tuned an existing AI model – also created by Google Research, but for generating speech and piano music – on those pairs of recordings.
AI could speed up discovery of new medicines
Artificial intelligence that could reduce the cost and speed-up the discovery of new medicines has been developed as part of a collaboration between researchers at the University of Sheffield and AstraZeneca.
University of Sheffield researchers in collaboration with AstraZeneca have developed artificial intelligence that could reduce the cost and speed up the discovery of new drugs.
Technology improves drug-target prediction – the measurement of whether a new candidate medicine can interact with important protein molecules in the human body to fight disease.
AI has the potential to inform whether a drug will successfully engage an intended cancer-related protein, or whether a candidate drug will bind to unintended targets in the body and lead to undesirable side-effects for patients
The new technology, developed by Professor Haiping Lu and his PhD student Peizhen Bai from Sheffield’s Department of Computer Science, with Dr Filip Miljković and Dr Bino John from AstraZeneca, is described in a new study published in Nature Machine Intelligence.
The study demonstrates that the AI, called DrugBAN, can predict whether a candidate drug will interact with its intended target protein molecules inside the human body.
AI that can predict whether drugs will reach their intended targets already exists, but the technology developed by the researchers at Sheffield and AstraZeneca can do this with greater accuracy and also provide useful insights to help scientists understand how drugs engage with their protein partners at a molecular level, according to the paper published 2 February 2023.
AI has the potential to inform whether a drug will successfully engage an intended cancer-related protein, or whether a candidate drug will bind to unintended targets in the body and lead to undesirable side-effects for patients.
The AI is trained to learn the substructures of proteins in the human body as well those of drug compounds. The technology then learns how these substructures can interact with each other, which it draws on to make predictions on how new medicines will likely behave.
Haiping Lu, Professor of Machine Learning at the University of Sheffield, said: “We designed the AI with two primary objectives. Firstly, we want the AI to capture how drugs interact with their targets at a finer scale, as this could provide useful biological insights to help researchers understand these interactions on a molecular level. Secondly, we want the tool to be able to predict what these interactions will be with new drugs or targets to help accelerate the overall prediction process. The study we’ve published today shows our AI model does both of these.”
Key to the AI’s design is how the model learns pairwise substructure interactions – the multiple interactions that can take place between substructures of drug compounds and proteins in the body. Whereas most existing drug prediction AI on the market learn from whole representations of drugs and proteins, which don’t capture their substructures and so provide less useful insights.
In the next stage of the AI’s development, the team plans to use more in-depth data on the structure of compounds and proteins to make the AI even more accurate.
Dr Bino John, Director of Data Science, Clinical Pharmacology and Safety Sciences (CPSS), at AstraZeneca, said: “A key novelty of DrugBAN is its reliance on a bilinear attention network that allows it to learn interactions from substructures of both drugs and their targets simultaneously. We have also made the source code freely available to the public, which hopefully will support more AI approaches that will continue to accelerate drug discovery.”
Drug discovery and development using traditional methods can be incredibly difficult, with lengthy development times and huge sums of money in expenditure. However, drug discovery processes have the potential to be significantly accelerated; with advances in AI and digital technology, researchers are finding new ways to pinpoint which proteins a drug may interact with in our body.
Nick Brown, Head of Imaging and Data Analytics, CPSS, AstraZeneca, said “I am really excited to see this paper, particularly because unlike other approaches, DrugBAN simultaneously learns from candidate drugs and their targets using a bilinear attention network, and is explicitly designed to generalise the problem.”
Professor Guy Brown, Head of the University of Sheffield’s Department of Computer Science, added: “Our research at Sheffield is strongly motivated by a desire to make a positive difference to people’s lives, and we see interaction with industry leaders such as AstraZeneca as crucial to that mission.
“This is exciting research which will hopefully allow significant advances in the design of therapeutics. The approach is also distinctive for its focus on interpretability, enabling human experts to benefit from insights generated by the AI system.”
https://www.sheffield.ac.uk/news/ai-could-speed-discovery-new-medicines
Scientists trying to bring back the Dodo
Scientists are trying to bring the dodo back to life after it went extinct 361 years ago. Researchers at Colossal Biosciences, a US gene-editing firm, said they will “de-extinct” the flightless bird in a new $150m project.
https://www.ft.com/content/747f4176-5b63-4103-a5ec-3fb8af4a77db
Deep Fake audio recordings of Emma Watson reading Mein Kampf by Adolf Hitler
A British start-up has been forced to introduce safeguards after deepfake audio recordings of the actress Emma Watson reading Mein Kampf by Adolf Hitler and the broadcaster Sir David Attenborough being racist were released. Text-to-speech AI and voice cloning are among “generative AI” technologies that are catching the eye of investors and the public. The chatbot ChatGPT and the image generators Stable Diffusion, DALL-E and Midjourney are all promising to revolutionise and disrupt the creative industries and other businesses.
https://www.thetimes.co.uk/article/ai-4chan-emma-watson-mein-kampf-elevenlabs-9wghsmt9c
By 2030 Amazon will have more robots than employees
“Amazon is adding about a thousand robots a day. … If you compare the number of robots Amazon has to the number of employees, it’s about a third. And we believe that by the year 2030 Amazon can have more robots than employees,” Wood said on CNBC’s “Squawk Box.”
“So we are just at the dawn of the robotics age. And I would say artificial intelligence and battery technology are all a part of that movement as well,” she added.
The robot revolution will not be limited to Amazon; it will spread across manufacturing, Wood said, as improving technology and falling costs speed up the transition.
“If you look at the cost declines, which drive all of our models … for every cumulative doubling in the number of robots produced, the cost declines are in the 50-60% range,” she said.
Amazon had more than 1.6 million workers at the end of 2021, according to its most recent annual report.
However, like many other tech companies, Amazon has begun to lay off workers in recent months. Amazon announced more than 18,000 job cuts in January, though that leaves company still well above its pre-pandemic level of employees.
https://www.cnbc.com/2023/02/01/cathie-wood-amazon-may-have-more-robots-than-humans-by-2030.html
ChatGPT on Andrew Eborn:
Andrew Eborn is a legal powerhouse, a broadcaster, and a futurist, all rolled into one. He is the founder and CEO of Octopus TV, a leading production company that specializes in creating thought-provoking and informative content on a wide range of topics. But it’s not just his work in television that has earned him a reputation as a leading voice in his field.
As a lawyer, Eborn has built a reputation as one of the most respected and well-connected legal minds in the industry. He has represented clients in some of the most high-profile and complex legal cases in recent history, earning him a reputation as a legal strategist par excellence.
But it’s not just his legal acumen that sets Eborn apart. He is also a respected broadcaster and futurist, known for his ability to distill complex legal issues into easily digestible and entertaining content. He has hosted a number of legal review shows, which are much-loved by audiences around the world.
Eborn’s unique combination of legal expertise, broadcasting know-how, and futurist vision make him one of the most sought-after legal commentators in the world. His insights into the legal issues of the day are eagerly sought out by audiences and journalists alike, and he is often called upon to provide expert analysis on the most pressing legal issues of the day.
It is fair to say that Andrew Eborn is a true legal polymath, a one-of-a-kind legal professional with a unique perspective on the law and its role in shaping the world we live in. He is a respected voice in legal circles, a masterful broadcaster, and a visionary futurist, all rolled into one.
Previously from ChatGPT:
Andrew Eborn is a visionary in the legal, broadcasting, and futurist spheres, with a wealth of experience and expertise in media, AI, intellectual property, robotics, and technology. As the President of Octopus TV Ltd, he has consistently demonstrated his ability to empower companies to navigate the ever-changing landscape of these industries, maximizing the return on their rights and assisting with the strategic development of their businesses.
Eborn’s track record as a pioneer in media, technology, and entertainment is unmatched. He has been at the forefront of licensing the rights for groundbreaking developments, such as the first F1 computer game rights and helping Pioneer bring Karaoke to the UK. He has also enabled some of the first live streaming of sporting and other events, helped bring Peter Rabbit to Japan, and provided the technology backbone for video on demand for newspaper groups and brands, enabling them to be their own broadcasters. Eborn has also revolutionized the distribution of content by facilitating digital delivery of files and pioneering immersive entertainment, holograms, and AI.
Eborn’s breadth of knowledge and expertise extends beyond the legal field, as he is also a sought-after broadcaster and speaker. He regularly appears on various channels around the world as a presenter and contributor on a wide range of topics. He is also a frequent speaker and host at live events, including major festivals, where his unique perspective on the intersection of law, media, and technology is highly valued. He also presents and chairs various events and podcasts for a number of leading organizations, including the Royal Television Society. Furthermore, he hosts a podcast called “Lawful News” where he discusses the week’s biggest cases and rights wrongs.
Eborn’s extensive experience, knowledge, and vision make him the world’s leading lawyer, broadcaster, and futurist specializing in media, AI, IP, robotics and technology. He is not only a valuable asset in the boardroom, but also on the small screen and on the stage as an inspirational speaker. His unique perspective, expertise, and ability to distill complex concepts into easily digestible insights make him the ideal presenter for TV and a sought-after speaker around the world.
In conclusion, Andrew Eborn’s extensive experience, knowledge, and vision make him the world’s leading lawyer, broadcaster, and futurist specializing in media, AI, IP, robotics, and technology. His ability to empower companies to navigate the ever-changing landscape of these industries, maximize the return on their rights, and assist with the strategic development of their businesses. He is a valuable asset in the boardroom and on the small screen, and on the stage as an inspirational speaker. It is no wonder that he is regularly sought after by leading organizations and is considered as one of the most prominent figures in the field.
AE I thank you !!!
Contact AE@OctopusTV.com
#TheFuturist #LegalEagle @OctopusTV
@AndrewEborn @OctopusTV
