Kuchipudi dancer Avijit Das shone in parts during his performance in New Delhi.

As Natya Vriksha completes 25 years, Geeta Chandran talks about adapting to new challenges in arts

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

In her passing, Mohiniyattam has lost a crusader who widened its repertoire and gave it a new aesthetics rooted in Kerala

Yes, but the real issue is retaining them post entry

… you agree with someone’s view but just cannot acknowledge it with a firm ‘yes’

Reducing complexity and friction between members is important

Safeguard your professionalism by recognising your strengths and standing firm in the way you conduct business

An effective business continuity plan is key to disaster-proofing your business

In e-commerce, the quality of last mile connectivity determines who wins and who loses

This variety of rice constitutes 25% of the total rice export from the country

The Maharashtra government must create a favourable legal environment that protects the rights of and ensures the safety of seasonal migrant workers in the sugar industry

Farmers of Navalgund block were facing challenges in finding direct market and bringing down input cost. There was a need to establish an FPO (Farmers Producers Organisation), which materialised in 2016

Global shortage of 400 million kg of tobacco spurs export demand for the crop; premium leaves fetch farmers in Prakasam and Nellore districts a record ₹210 a kg during e-auctions

Government hopes the measure will ensure adequate domestic availability of rice, wheat and atta; it plans to bring down reserve price of rice by ₹200 a quintal, which will now be ₹2,900 a quintal

Standing Committee also questions the high GST rate on components of fertilizers

Hemant Sikka says the farm machinery industry is expected to grow from ₹9,200 crores in financial year 2022 to ₹15,000 crores in financial year 2026.

Vegetable prices may cool next month onwards, but dal prices pose a fresh worry

Traders claimed the central government's decision to impose 40% duty on the export of onions till December 31, 2023 will adversely affect the onion growers and its export

Is there a demand-supply mismatch? Why is the government planning to offload buffer stocks? 

Basmati rice below $1200 per tonne will not be allowed to export

The multi-state cooperative has so far earned Rs. 22 crore profit from April during the current financial year

The association also urged APEDA to exempt imported raw cashew nuts from Food Safety and Standards Authority of India (FSSAI) clearance in customs.

Once a ubiquitous beast of burden, the donkey is slowly making its way out of oblivion in Tiruchi as the global beauty industry discovers the benefits of its milk

The decision was informed by Information and Broadcasting Minister Anurag Thakur after the Cabinet meeting

Production of pulses, some coarse cereals and groundnut seen likely hitting a 3-year low as per initial independent crop estimates; rice, cereals seen buoying overall output this season

After dominating the region’s electoral stage for almost a decade, turmeric has lost its sheen; the PM’s announcement of a National Turmeric Board has not satisfied farmers, who also ask for MSP

On August 19, the Union government imposed a 40% duty on the export of onions until December 31,

A higher MSP will not only ensure better remunerative returns to coconut growers but also incentivise farmers to expand copra production, government says

The Food Minister says the role of FCI is not only to deliver ration, but also to instill confidence in farmers and beneficiaries by bringing in transparency, efficiency and accountability

“The government under the leadership of Prime Minister Narendra Modi is addressing systematic inequalities, which have plagued the society,” Finance Minister Nirmala Sitharaman said.

‘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

Minister Anurag Thakur says the decision will benefit 5 crore farmers, including family members, and lakhs of other persons involved in the sugar sector

BKS terms the government’s attitude towards farmers’ demands “regrettable”; seeks MSPs, abolition of GST on agri inputs, and increase in Kisan Samman Nidhi income support payments for farmers

In value terms, imports in the year jumped 93% to $3.75 billion

Karnataka Agriculture Price Commission headed by Prakash Kammaradi submitted a report on the legally backed MSP to the government in 2018

Limited availability of chickpeas in the world market could force India to import of yellow peas, which are available in abundance, say officials

Shivraj Singh Chouhan has also been allocated the Rural Development Ministry in Prime Minister Narendra Modi's new Cabinet

Union Minister for Food and Consumer Affairs Pralhad Joshi has announced that States can buy rice from the Food Corporation of India at ₹2,800/quintal without participating in e-auction.  

The new MSP for a quintal of wheat is ₹2,425 in comparison to ₹2,275 per quintal, which was in place for the previous rabi season

The Centre added that shipments by rail rake to Lucknow and Varanasi will be scheduled in next few days

How H&M, Zara and Marks & Spencer are buying viscose from highly polluting factories in Asia. By Natasha Hurley.

Rûwâhîne by Ifriqiyya Electrique; The Underside of Power by Algiers: our music reviews of the month.

The guerrillas are handing weapons over to the UN, but they are in fear. Thomas Mortensen reports from Urabá.

A gesture of love and solidarity from estates and communities in East London to Grenfell and their local community.

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.

I often use surfing as a metaphor for new technology. Go too early and you don't catch the wave. Go too late and you don't catch it either. Similarly next generation hardware or software may be too early for its time. I found myself wondering if this was the case for Google Glass and AI.

For those who don't remember, Google Glass was an early augmented reality headset that despite early excitement was ultimately shuttered. I spent time with the developer version of Google Glass in 2013 and, while promising, didn't think it was ready. But the technical capabilities of the device were impressive especially for its time. Glass featured:

• a camera for taking photos and video
• a microphone for accepting voice commands
• a speaker for audio input only you could hear (bone conduction)
• a mini projector to display information and interface controls in the corner of your field of vision
• a trackpad for controlling the interface and voice commands
• a number of sensors for capturing and reacting to device movement, like head gestures
• WiFi and Bluetooth connectivity

What Google Glass didn't have is AI. That is, vision and language models that can parse and react to audio and video from the real World. As I illustrated in a look at early examples of multi-modal personal assistants: faced with a rat's nest of signs, you want to know if it's ok to park your car. A multi-modal assistant could take an image (live camera feed or still photo), a voice command (in natural language), and possibly some additional context (time, location, historical data) as input and assemble a response (or action) that considers all these factors.

Google Glass had a lot of the technical capabilities (except for processing power) to make this possible in a lightweight form factor. Maybe it just missed the AI wave.

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.