This Himalayan Buddhist hamlet in Arunachal Pradesh is modernising at its own pace

She's sexy and she knows it!

Shah Rukh Khan will return to television as the host of a Hindi show called TED Talks India: Nayi Soch, which will feature inspirational speakers and big ideas.

Shah Rukh Khan makes a comeback to the small screen.

Max Verstappen won his second Formula 1 season title at Suzuka in 2022, and he dominated in Japan last season as he won his third straight title.

Sukhjeet Singh overcame the "toughest" phase of his life to earn a spot in the Olympic-bound Indian men's hockey squad and is determined to prove his worth.

Sukhjeet Singh is one of the five debutants — Sanjay, Abhishek, Rajkumar Pal, and Jarmanpreet Singh — who have joined the 11 members of Tokyo Olympic bronze medalist team for the Paris Games.

As the city soaks in the spirit of the holy month of Ramzan, we have crispy potato samosas, piping hot kebabs, and refreshing nungu milk for iftar at Karumbukkadai and Podanur

Insignificant market access, introduction of new issues, a double whammy

If the household budget/ cost of living was Rs 100 in September 2021, it has increased by Rs 12 in both the US and India, but it has increased by Rs 20 in Germany and Rs 23 in the UK: Report

Trial run from Kochi to Mattupetty dam completed in 30 minutes. Tourism stakeholders say the service will be a game changer for a district that had no air connectivity hitherto

Cambridge, MA. : National Bureau of Economic Research, 2023

Bollywood actor Shah Rukh Khan receives threat call and extortion demand for ₹50 lakh

As per preliminary information, the threat call to the actor was made by a phone number registered in the name of Faizan, says Raipur's Senior Superintendent of Police Santosh Singh

Bollywood looked gorgeous as they stepped out on the red carpet at the IIFA (International Indian Film Academy) awards in Abu Dhabi.

Reliance would like to build AI infrastructure in the country that would make a similar impact like Jio did for telecom infrastructure, says Mukesh Ambani, speaking at the Nvidia AI summit in Mumbai

'Laapataa Ladies opened a lot of doors for me.''I have gotten so much love from audiences and seniors in the industry that it's overwhelming.''I get calls from superstars. I'm holding my heart and it's like, "Oh my God, they are calling me? I am their fan and they love my work!"'

'I'm there in every frame of this film.''The film is named after the character that I play.''It's about a feeling like you are capable of shouldering a film entirely on your own, which is a belief that I may not have in myself always.'

'I'm happy piggybacking on his stardom.'

Dubai-based siblings have seemingly decided to offer the domain to Reliance free of charge, according to their website.

The two Bharatanatyam dancers paid tribute to M.K. Saroja through their abhang-based performance

‘We intend to bring a revolutionary change in the agriculture sector with a special focus on promoting animal husbandry,’ Sukhvinder Singh Sukhu tells the hill State’s milk producers

He puts his life on the line to protect the Democratic Republic of Congo's national parks.

As the number of highly capable large language models (LLMs) released continues to quickly increase, I added the ability to test new models when they become available in the Ask Luke conversational interface on this site.

For context there's a number of places in the Ask Luke pipeline that make use of AI models to transform, clean, embed, retrieve, generate content and more. I put together a short video that explains how this pipeline is constructed and why if you're interested.

Specifically for the content generation step, once the right content is found, ranked, and assembled into a set of instructions, I can select which large language model to send these instructions to. Every model gets the same instructions unless they can support a larger context window. In which case they might get more ranked results than a model with a smaller context size.

Despite the consistent instructions, switching LLMs can have a very big impact on answer generation. I'll leave you to guess which of these two answers is powered by OpenAI's GPT-4 and which one comes from Antrhopic's new (this week) Claude 3.5 Sonnet.

Some of you might astutely point out that the instruction set could be altered in specific ways when changing models. Recently, we've found the most advanced LLMs to be more interchangeable than before. But there's still differences in how they generate content as you can clearly see in the example above. Which one is best though... could soon be a matter of personal preference.

Thanks to Yangguang Li and Sam for the dev help on this feature.

Over the years, I've given more than 300 presentations on design. Most of these have been accompanied by a slide deck to illustrate my points and guide the narrative. But making the content in these decks work well with the Ask Luke conversational interface on this site has been challenging. So now I'm trying a new approach with AI vision models.

To avoid application specific formats (Keynote, PowerPoint), I've long been making my presentation slides available for download as PDF documents. These files usually consist of 100+ pages and often don't include a lot of text, leaning instead on visuals and charts to communicate information. To illustrate, here's of few of these slides from my Mind the Gap talk.

In an earlier article on how we built the Ask Luke conversational interface, I outlined the issues with extracting useful information from these documents. I wanted the content in these PDFs to be available when answering people's design questions in addition to the blog articles, videos and audio interviews that we were already using.

But even when we got text extraction from PDFs working well, running the process on any given PDF document would create many content embeddings of poor quality (like the one below). These content chunks would then end up influencing the answers we generated in less than helpful ways.

To prevent these from clogging up our limited context (how much content we can work with to create an answer) with useless results, we set up processes to remove low quality content chunks. While that improved things, the content in these presentations was no longer accessible to people asking questions on Ask Luke.

So we tried a different approach. Instead of extracting text from each page of a PDF presentation, we ran it through an AI vision model to create a detailed description of the content on the page. In the example below, the previous text extraction method (on the left) gets the content from the slide. The new vision model approach (on the right) though, does a much better job creating useful content for answering questions.

Here's another example illustrating the difference between the PDF text extraction method used before and the vision AI model currently in use. This time instead of a chart, we're generating a useful description of a diagram.

This change is now rolled out across all the PDFs the Ask Luke conversational interface can reference to answer design questions. Gone are useless content chunks and there's a lot more useful content immediately available.

Thanks to Yangguang Li for the dev help on this change.

The Ask Luke feature on this site uses the thousands of articles, hundreds of PDFs, dozens of videos, and more I've created over the years to answer people's questions about digital product design. Since it launched a year ago, we've been iterating on the core of the Ask Luke system: retrieving relevant content to improve answers.

The most important job of any product interface is making its value clear and accessible to people. Most apps resort to some form of onboarding to accomplish this, but it's exponentially more impactful to experience value than to be told it exists. Likewise it's much more effective to learn through using an interface than through a tutorial explaining it.

These two factors make the seemingly simple job of "getting people to product value" quite difficult. Compounding the issue is that fact that interface solutions that accomplish this often feel simple and obvious -but only after they're uncovered. So iterating to an interface that intuitively conveys value and purpose is usually an iterative process.

That's a long-winded introduction, but it's important context for the changes we made to Ask Luke. The purpose and value of this feature is to pull the most relevant bits of my writings, videos, audio, and files together to answer people's questions about digital product design. So we made a bunch of changes to make that even more front and center -to make how Ask Luke works more obvious.

Now as answers to people's questions stream in, we add citations to the relevant articles, videos, PDF, etc. being used to answer a question in real-time. We also add these citations to the list of sources on the right dynamically instead of all at once before a question is answered.

Before people were able to select any given source and view it in the Ask Luke conversational UI. With these updates, they are also taken to the relevant part of a source: to the relevant point in a video; to the relevant page in a PDF. Since this is easier to see than read about, here's a quick video demonstrating these changes and hopefully making the value and purpose of Ask Luke a bit more obvious.

• Integrated Audio Experiences & Memory: enabling specific content experiences within a conversational UI
• Expanding Conversational User Interfaces: extending chat user interfaces to better support AI capabilities
• Integrated Video Experiences: adding video-specific experiences within conversational UI
• Integrated PDF Experiences: unique considerations when adding PDF experiences
• Dynamic Preview Cards: created on the fly to improve sharing answers
• Text Generation Differences: testing the impact of AI new models
• PDF Parsing with Vision Models: using AI vision models to extract content form PDFs

Acknowledgments

Big thanks to Sidharth Lakshmanan and Sam Breed for the engineering lift on these changes.

Since launching the Ask Luke feature on this site last year, we've added the ability for the system to respond to questions about product design by citing articles, videos, audio, and PDFs. Now we're introducing the ability to cite the thousands of images I've created over the years and reference them directly in answers.

Significant improvements in AI vision models have given us the ability to quickly and easily describe visual content. I recently outlined how we used this capability to index the content of PDF pages in more depth making individual PDF pages a much better source of content in the Ask Luke corpus.

We applied the same process and pipeline to the thousands of images I've created for articles and presentations over the years. Essentially, each image on my Website gets parsed by a vision model and we add the resulting text-based description to the set of content we can use to answer people's design questions. Here's an example of the kinds of descriptions we're creating. As you can see, the descriptions can get pretty detailed when needed.

If someone asks a question where an image is a key part of the answer, our replies not only return streaming text and citations but inline images as well. In this question asking about Amazon's design changes over the years, multiple images are included directly in the response.

Not only are images displayed where relevant, the answer refers to them and often refers to the contents of the image. In the same Amazon navigation example, the answer refers to the green and white color scheme of the image in addition to its contents.

Now that we've got citations and images steaming inline in Ask Luke responses, perhaps adding inline videos and audio files queued to relevant timestamps might be next? We're already integrating those in the conversational UI so why not... AI is a hell of a drug.

Further Reading

Additional articles about what I've tried and learned by rethinking the design and development of my Website using large-scale AI models.

• New Ways into Web Content: rethinking how to design software with AI
• Integrated Audio Experiences & Memory: enabling specific content experiences
• Expanding Conversational User Interfaces: extending chat user interfaces
• Integrated Video Experiences: adding video experiences to conversational UI
• Integrated PDF Experiences: unique considerations when adding PDF experiences
• Dynamic Preview Cards: improving how generated answers are shared
• Text Generation Differences: testing the impact of AI new models
• PDF Parsing with Vision Models: using AI vision models to extract PDF contents
• Streaming Citations: citing relevant articles, videos, PDFs, etc. in real-time
• Streaming Inline Images: indexing & displaying relevant images in answers

Acknowledgments

Big thanks to Sidharth Lakshmanan and Sam Breed for the development help.

At the JW Marriott Phuket Resort & Spa, the family is a special bond to celebrate

Edmonton, Alberta : Brush Education Inc., [2023]

Poornima Indrajith effortlessly transforms for the role of a lifetime in Rajeev Ravi’s opus Thuramukham

TheWriter of two of the best period dramas in the recent history of Malayalam cinema, Gopan Chidambaram talks speaks about how Thuramukham, a play written by his father in 1968, was adapted to the screen and why he often gravitates towards historical tales

Warszawa : Wydawnictwo Naukowe Scholar, 2023.

London : Cassell and Company Ltd., [1938]

London : Bennett & Bloom, 2006.

Suneet Singh Tuli: creator of India's groundbreaking £25 Aakash tablet computer. The entry-level model of the Aakash budget tablet, which is revolutionising education in the developing world, should be available to buy online in the UK for £29.99 by the end of the year.

Since 2015 the UK government has been trying to impose restrictions on access to porn. All of the legal measures needed to do so have passed and now it is only a matter of time until changes start to happen across the web. But the idea (and the execution) is fundamentally flawed. The UK's film certification board, an organisation with a limited digital background, has been put in charge of implementing the policy and one of the main age verification systems is owned by the world's largest porn company. The result? Potentially profound and damaging implications for privacy and a deluge of data on the private habits of millions of people just waiting to be hacked. Read more about the UK porn block: https://www.wired.co.uk/article/porn-block-ban-in-the-uk-age-verifcation-law #Privacy #Censorship #UK CONNECT WITH WIRED UK Web: http://po.st/WiredVideo Twitter: http://po.st/TwitterWired Facebook: http://po.st/FacebookWired Google+: http://po.st/GoogleWired Instagram: http://po.st/InstagramWired Magazine: http://po.st/MagazineWired Newsletter: http://po.st/NewslettersWired ABOUT WIRED UK WIRED brings you the future as it happens - the people, the trends, the big ideas that will change our lives. An award-winning printed monthly and online publication. WIRED is an agenda-setting magazine offering brain food on a wide range of topics, from science, technology and business to pop-culture and politics.

To find out how well the latest vegan burger offering fares from a professional point of view – and if they really do give actual meat a run for its money – we asked chef Marcus Samuelsson to put his tastebuds to task: with his mix of southern American, Ethiopian and Swedish food, Samuelsson knows what makes for a delicious burger. Samuelsson provided the menu for the Obama Administration’s first State dinner, had a three-star restaurant review from The New York Times at the age of 24, and owns a number of restaurants including Red Rooster – in both Harlem, New York, and Shoreditch, London – and, most recently, Marcus in Montreal, Canada. To give each of the seven vegan burgers in our test a fair start, we dressed each pattie with a tofu-based mayonnaise, vegan cheese, a slice of tomato, lettuce and red-onion dressing before topping it off with a vegan brioche bun. The testing took place in Samuelsson's Shoreditch-based restaurant Red Rooster at The Curtain Hotel. Only burgers available to buy in UK shops were eligible (sorry, no Impossible Burger yet). Here's our pick of the best vegan burgers you can buy right now. Read the guide on WIRED UK: https://www.wired.co.uk/article/best-vegan-burger-uk #vegan #veganburger #veganfood

Automation Anywhere presents a conversation with its CEO and Cofounder, Mihir Shukla, and WIRED's Jahna Berry, as part of WIRED25, WIRED's second annual conference in San Francisco. (Sponsored Content)

WIRED brings you the future as it happens - the people, the trends, the big ideas that will change our lives.

If you close your eyes and picture an apple, how clear is that apple in your mind? Most people can visualise images in their head instantaneously - this known as the mind's eye. But in 2015, a scientific study shed new light on the relatively unheard-of phenomenon known as aphantasia, a mental blindness where the brain is unable to call images to the mind eye. This short documentary uncovers the root cause of a person's emotional detachment from people and events - and the unexpected advantages that come with it. Alex Wheeler shares the story of how his experiences with aphantasia have affected his life, particularly his grieving process after losing his mum, as he seeks answers from Adam Zeman, Professor of Cognitive and Behavioural Neurology at the University of Exeter Medical School. WIRED also talks to artist and YouTuber Amy Right, better known as @AmyRightMeow, who shares their experiences with aphantasia and how it feeds their creative process. Produced as part of WIRED Health https://www.wired.co.uk/partnerships/wired-health Director: @Simon Mulvaney Producer: Anna O'Donohue Featuring: Alex Wheeler , Adam Zeman, Amy Right Field Producer: Lewis Faithfull Studio Cinematographer: Dan McPake Studio Art Director: Deborah Du Vernay Animation & VFX: Run Zebra Run Original Music Composition: Liam Hennessy and Joe Danher VHS Digitised by EachMoment – https://eachmoment.co.uk Subscribe to WIRED UK ► https://www.youtube.com/wireduk?sub_confirmation=1 Visit the WIRED website ► https://www.wired.co.uk Subscribe to WIRED Magazine ► https://www.wired.co.uk/subscribe Sign up for one or more of our WIRED newsletters: https://www.wired.co.uk/newsletters CONNECT WITH WIRED Facebook: https://www.facebook.com/wireduk Instagram: https://www.instagram.com/wireduk Twitter: https://twitter.com/wireduk LinkedIn: https://www.linkedin.com/company/wired-uk ABOUT WIRED WIRED brings you the future as it happens - the people, the trends, the big ideas that will change our lives. An award-winning printed monthly and online publication. WIRED is an agenda-setting magazine offering brain food on a wide range of topics, from science, technology and business to pop-culture and politics.

Russia has been launching some of the most disruptive cyberattacks in history against Ukraine for some years now. WIRED's Andy Greenberg, author of the book "Sandworm," walks us through the history of Russia's cyberattacks against Ukraine.

Pulitzer Prize-winning oncologist Siddhartha Mukherjee takes readers on an inward journey to discover the building blocks and their place in the human body