The pandemic has brought into focus the role of the Chief People Officer, who has to handle unprecedented circumstances that are not covered in the rule book

Minister Carlos Fávaro offers transfer of technology to India to boost cooperative production

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

PM Modi made his comments while inaugurating the pilot project of “world’s largest grain storage plan”, which is being done across 11 States

Farmers hardly get 30% of the price paid by the consumers. This will increase if MSP is guaranteed

The country is among those most vulnerable to water management risks, and has the poorest access to basic services, including water, among G-20 economies, the rating major flagged

Britain’s largest festival about refugees and sanctuary is more relevant than ever, writes Lydia Noon.

The author of The Reluctant Fundamentalist talks to Graeme Green about extremism, the refugee crisis and feeling at home in the past.

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.

When working through the early stages of a product design, it's common that labels for objects and actions emerge organically. No one is overly concerned about making these labels consistent (yet). But if this proliferation of terms doesn't get reined in early, both product design and strategy get harder.

Do we call it a library, a folder, a collection, a workspace, a section, a category, a topic? How about a document, page, file, entry, article, worksheet? And.. what's the difference? While these kinds of decisions might not be front and center when working out designs for a product or feature, they can impact a lot.

For starters, having clear definitions for concepts helps keep teams on the same page. When engineering works on implementing a new object type, they're aligned with what design is thinking, which is what the sales team is pitching potential customers on. Bringing a product to life is hard enough, why complicate things by using different terms for similar things or vice versa?

Inconsistent terms are obviously also a comprehension issue for the people using our products. "Here's it's called a Document, there it's called an Article. Are those the same?" Additionally, undefined terms often lead to miscellaneous bins in our user interfaces. "What's inside Explore?" When the definition of objects and actions isn't clear, what choice do we have but to drop them into vague sounding containers like Discover?

The more a product gets developed (especially by bigger teams) the more things can diverge because people's mental model of what terms mean can vary a lot. So it's really useful to proactively put together a list of the objects and actions that make up an application and draft some simple one-liner definitions for each. These lists almost always kick off useful high-level discussions within teams on what we're building and for who. Being forced to define things requires you to think them through: what is this feature doing and why?

And of course, consistent labels also ease comprehension for users. Once people learn what something means, they'll be able to apply that knowledge elsewhere -instead of having to contend with mystery meat navigation.

We tend to ignore the view of people around us. We also tend not to value the potential around us. The result is someone like the S&P grades us negative and gives us Gyan!

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

London ; Philadelphia : Jessica Kingsley Publishers, 2024.

Cincinnati : University of Cincinnati Press, 2021.

New York : Peter Lang , 2024.

Cham, Switzerland : Springer, [2024]

Aanu, starring Sajitha Madathil and Namitha Pramod, will be screened at the 27th International Film Festival of Kerala

The Mantle twins want to “change the way women give birth” — the body horror subgenre has always been nimble and alert to the red-button political issues of the day

Actor Allu Arjun and Asian Cinemas launch AAA Cinemas in Hyderabad said to be the only multiplex in south India to have an LED screen

Director Vivek Athreya opens up on his writing techniques, the art of listening and how films of K Vishwanath, Mani Ratnam, Krishna Vamsi and Mysskin influenced him in his formative years

Maze operators use virtual machines to spread the ransomware

Every time a transaction is initiated, the backend runs a check whether the customer is using the bank’s mobile app

Shailendra Katyal, Managing Director, Lenovo India, on the company’s services-led transformation

A well-powered enterprise laptop that delivers performance and features in the right form factor  

Singapore : Horizon Books, 2002.

Princeton : Princeton University Press, [2007]

New York : Thames & Hudson in association with Cooper-Hewitt, National Design Museum, Smithsonian Institution, 2002.

London : Pan Books Ltd : William Heinemann Ltd, 1986.

Tokyo ; Rutland, Vermont ; Singapore : Tuttle Publishing, 2020.

London : The Folio Society, 1986

Lublin : Wydawnictwo Werset, 2023.

[France] : uniFrance, [2015]

Universal City, CA : Vivendi Entertainment, [2011]

Tokyo : Charles E. Tuttle Company, [1964]

New York : Grove Press, 1960.

New York : Grove Press, 1960.

New York : Henry Holt and Company, 1987.

Karachi : Oxford University Press, 2017.

Paris : Paris Musées : Musée d'Art moderne de Paris, [2023]

Moskva : Samolet, 2000.

Andros : Basil and Elise Goulandris Foundation, [2000]

New Delhi : Lustre Press : Roli Books, [2004]

London : Pan Books, 1974.

New Haven : Yale University Press, [1981]

Princeton : Princeton University Press, [2023]

Chiyoda-ku, Tokyo, Japan : Japan Publishing Industry Foundation for Culture (JPIC), 2023.

London : Bloomsbury, [2016]