Future Today #138 - Artificial Lies · Megatrends · Algorithms · Fei-Fei Li · TED AI
David Alayón
Chief Executive Officer @ Innuba · Innovation Advisor @ Mindset · Fellow @ Acumen · Professor @ IE & Headspring · Author of UPGRADE · Futures & Foresight enthusiast
?? Welcome to Future Today! A newsletter for those curious about social innovation, disruptive technologies and futures studies. In it I share weekly articles, reports and interesting links, and recommendations of books, movies, series, events and courses. We are already more than 15,000 people! Do not hesitate to subscribe!
?? At Innuba, we design positive futures from complex presents. We've been helping organizations and leaders for over 8 years to understand the complex present, imagine positive futures, and make them a reality, through disruptive innovation, collaboration ecosystems, humanist technology, and new narratives. Shall we talk? Leave me a message!
?? How strategic foresight can help leaders plan for a changing world. Governments have a responsibility to plan for the long-term, which includes anticipating the unexpected, particularly in today’s increasingly uncertain world. Strategic foresight is a methodology within future studies that can help with this by enabling decision-makers to identify and respond to emerging opportunities and challenges in a timely way. If it’s supported by clear mandates and resources, strategic foresight can become part of an organization’s culture, helping it to prepare for the future.
??? AI Systems Are Learning to Lie and Deceive, Scientists Find. AI models are, apparently, getting better at lying on purpose. Two recent studies — one published this week in the journal PNAS and the other last month in the journal Patterns — reveal some jarring findings about large language models (LLMs) and their ability to lie to or deceive human observers on purpose.
?? The teens making friends with AI chatbots. Teens are opening up to AI chatbots as a way to explore friendship. But sometimes, the AI’s advice can go too far. For many Character AI users, having a space to vent about their emotions or discuss psychological issues with someone outside of their social circle is a large part of what draws them to the chatbots.
?? The Social Cost of Algorithmic Management. To achieve efficiencies and reduce costs, more and more companies are managing their employees by algorithm. In this article, the authors present some of the first research findings concerning the effects of algorithmic management on workplace dynamics. One important finding is that employees managed by algorithms are less likely than colleagues managed by people to help others. The authors conclude with suggestions for how companies who want to use algorithmic management can mitigate its negative effects.
?? 10 megatrends shaping our future. In humanity’s journey towards the future, it has become critical for societies and governments to develop the capabilities and skills necessary for comprehensive adaptability that enable them to embrace rapid changes. They need to be prepared to analyse signals and evolving megatrends that will shape the future. These megatrends must be studied in a practical and participatory manner to formulate future scenarios that prioritise maximising available opportunities and leveraging them in a way that serves humanity’s interests above all else.
TV Series: Dark Matter (2024 - ) - Blake Crouch
?? ?? Do you want to know all the movies and series of Future Today, here is the complete list? And do you want to know all the books, here is the list?
?? Geoffrey Hinton in conversation with Fei-Fei Li — Responsible AI development. U of T Professor Emeritus Geoffrey Hinton is joined by Stanford University Professor Fei-Fei Li for a special talk on ethical AI, presented by Radical Ventures and hosted by the University of Toronto. They address the ethical considerations of AI development and its advancement — as well as its potential to solve some of the world’s most pressing problems. They also discuss their collaboration on one of the most important milestones in the history of modern AI.
?? Why shifting from prediction to foresight can help us plan for future disruption. As the world becomes more complex, foresight methodologies account for a greater set of possible futures. Scenario development, a foresight methodology, is an alternative to prediction which can help map new possibilities. Foresight may predict possible futures but more importantly, it allows for preparation.
?? Why governance needs Future Design. There are many reasons why we care about the long-term effects of our decisions on our family, our neighbours, our community and our planet. Yet research shows we are ill-equipped to value the future in our decision making. This is one of the reasons why SOIF is delighted to support members of our network who are testing and sharing new approaches to tackle this. Innovative methods like Future Design can help to build governance fit for the challenges we face.
? Announcing AI-adapted multilingual TED Talks, unblocking language barriers. At TED, we believe that ideas are universal and that they should be accessible to everyone. Yet language barriers often hinder access to our talks, many of which are delivered in English. To tackle this issue head-on, we’re expanding our multilingual initiatives, building on the success of TED’s subtitling program by combining human and artificial intelligence. This approach aims to enhance inclusivity and enrich the experiences for TED’s diverse global audiences.
领英推荐
??? AI Is Gathering a Growing Amount of Training Data Inside Virtual Worlds. In recent years, due to a striking improvement in the fidelity and realism of computer graphics technology, simulation is increasingly being used to accelerate the development of these algorithms. Waymo, for example, says its autonomous vehicles have already driven some 20 billion miles in simulation. In fact, all kinds of machines, from industrial robots to drones, are gathering a growing amount of their training data and practice hours inside virtual worlds.
Asking ChatGPT
In this section, the responses from ChatGPT have not been edited and I do not consider this Generative AI as an oracle. These are not presented as truth but as an experiment to observe and reflect on Gen AI.
???? Describe this image and imagine what could happen:
?? The image shows a dark gray cat with yellow eyes playing with a white cable. Next to the cat, there is a transparent glass jar filled with colorful candies. The cat seems to be on a wooden table.
We could imagine that while the cat continues playing with the cable, it might end up knocking the jar of candies to the floor. The candies would scatter all over the room, creating a colorful mess. The cat would probably get scared by the noise of the jar breaking and the candies rolling everywhere, and might run off to hide.
???? What if it plays with the cable by pulling it? Could it knock something to the floor?
?? If the cat continues playing with the cable and pulls on it, it's likely that something will end up falling to the floor. In this image, if the cable is connected to something heavy or fragile on the table, the cat might pull that object and cause it to fall. There's also the possibility that the jar of candies, which is near the cat, could be pushed or knocked over if the cat pulls the cable forcefully and moves the table. This would result in the candies spreading on the floor and possibly breaking the jar, creating a considerable mess.
???? Now look at this image. What do you think could have happened?
?? In this image, we see a gray and brown cat next to a toppled plant pot on the floor. The soil and the plant are scattered around the fallen pot. It is likely that the cat was playing near the pot or even with the plant itself, causing the pot to fall and spill its contents on the floor. The cat's expression, looking up, might suggest a mix of curiosity and innocence, as if it is trying to understand what happened or waiting for its owner's reaction.
I have always been convinced that the only way to get artificial intelligence to work is to do the computation in a way similar to the human brain. That is the goal I have been pursuing. We are making progress, though we still have lots to learn about how the brain actually works - Geoffrey Hinton
?? What has this newsletter sparked in you? Any thoughts? Leave a comment on this article and we'll generate an interesting conversation between all of us.
???? If you liked it... Leave a comment! Share it! Don't be shy! And subscribe! If you want to get in touch with me, ping me at [email protected].
Optimizing logistics and transportation with a passion for excellence | Building Ecosystem for Logistics Industry | Analytics-driven Logistics
5 个月What steps can leaders take to ensure that their strategic foresight plans are inclusive and considerate of diverse perspectives? #diversity #inclusion #strategicforesight.