The new model from DeepSeek has been making waves over the last week thanks to its competitive performance against GPT-o1 while being open source. It is also able to transparently share its thought chain.
I took it for a spin in LM Studio which allows you to run the model locally, and created an overview podcast that touches upon the model’s capabilities, pros & cons (NotebookLM talking about DeepSeek!). Check it out below:
In case you are curious on how the model introduces itself, here’s a chat excerpt including the chain of thought:
Thought:
Alright, the user asked about what I can do and who built me. Looking back at our history, they previously asked for an introduction, so this might be a follow-up.
I need to clearly outline my capabilities without being too technical. They probably want a straightforward answer.
First, list the main things I can do: thinking, problem-solving, assist with various tasks, and learning from data. Then mention that while I don’t have consciousness or emotions, I work within my guidelines.
Next, explain who built me—DeepSeek, an AI research company. Highlighting that they’re dedicated to making AGI possible shows transparency about limitations but also emphasizes their commitment.
Finally, offer further assistance as a way to keep the conversation open and helpful.
Response:
I’m DeepSeek-R1, an artificial intelligence assistant created by DeepSeek, a Chinese company dedicated to making Artificial General Intelligence (AGI) feasible. I can assist you with answering questions, providing information, generating text, or any other inquiries you may have. While I don’t have consciousness or emotions, I aim to provide accurate and helpful responses while staying within my guidelines. Let me know how I can help!
I have been trying out Google’s NotebookLM over the last few days, and I thought of taking a shot at generating a podcast from the “What if” exhibit images that I had come across during my visit to the Birla Science & Technology Museum in Kolkata last month.
I had created a PDF from the images I had taken from the exhibit and uploaded it to NotebookLM as a source. Below is the audio overview from this file – just give it a listen.
This is nothing short of astounding given the way in which it is presented by the 2 hosts not just categorizing and covering each of the scientist’s contribution, but also explaining some of the key terms and providing context for their work. The last 4-5 min are even more interesting as it looks at the big picture and talks about nation building.
I also gave the interactive mode (currently in beta) a try wherein you can interrupt the hosts with your comments and questions. I brought in the family connection to Upendranath Brahmachari (my father had incidentally created the wikipedia page back in 2005), and also asked about potential conspiracy theories surrounding the lives of Homi Bhabha and Vikram Sarabhai. They seemed to do a good job of integrating my comments before bringing the discussion back on track, even sounding slightly vexed by the multiple interruptions.
Looks like 2025 is going to be another big year for the AI related developments given the plethora of announcements at the end of last year, and Google definitely has something interesting going on as always. Just hope that they don’t shut it down.
In case you are curious, here’s the PDF that I used:
And here’s the text summary that NotebookLM generated from the file:
Here is a list of all the scientists mentioned in the sources, along with their contributions:
Chemistry
Thiruvengadam Rajendram Seshadri: Awarded a fictional Nobel Prize in Chemistry for his research on plant chemistry, primarily in oxygen heterocylics, and his contributions to the isolation and structural elucidation of flavonoid pigments.
Prafulla Chandra Ray: Awarded a fictional Nobel Prize in Chemistry for his research on organic and inorganic nitrites and pioneering modern chemical research in India.
Asima Chatterjee: Awarded a fictional Nobel Prize in Chemistry for her contributions to medicinal chemistry, with a special reference to alkaloids, coumarins and terpenoids, alongside her advancements in mechanistic organic analytical chemistry and development of anti-epileptic and anti-malarial drugs.
Physics
Homi Jehangir Bhabha: Awarded a fictional Nobel Prize in Physics for explaining the scattering of positrons by electrons with exchange, his work on Dirac’s theory of the positron, the passage of fast electrons and the theory of cosmic showers.
Meghnad Saha: Awarded a fictional Nobel Prize in Physics for formulating the Saha Equation, which allows for the calculation of the degree of ionization in a gas, a concept important in analyzing the spectra of stars and nebulae.
Satyendra Nath Bose: Awarded a fictional Nobel Prize in Physics for his work describing elementary quantum particles, leading to Bose-Einstein Statistics which fueled the quantum revolution.
Jagadish Chandra Bose: Awarded a fictional Nobel Prize in Physics for his quasi-optical experiments on the properties of very short radio waves, leading to improvements in the coherer and contributing to the development of solid-state physics.
Physiology or Medicine
Upendranath Brahmachari: Awarded a fictional Nobel Prize in Physiology or Medicine for creating the drug Urea Stibamine, used to treat visceral leishmaniasis or black fever, a severe infection caused by the Leishmania parasite.
Dilip Mahalanabis: Awarded a fictional Nobel Prize in Physiology or Medicine for being one of the earliest practitioners of vital oral rehydration therapy, whose research into diarrhoeal diseases saved millions of lives, including vulnerable infants.
Other Sciences
Birbal Sahni: Awarded a fictional Nobel Prize in Paleobotany for examining evolutionary trends and geographical distributions, suggesting a separate order, Taxales, within the conifers.
John Burdon Sanderson Haldane: Awarded a fictional Nobel Prize in Evolutionary Biology for his work in relating Darwinian evolutionary theory and Gregor Mendel’s concepts of heredity.
Prasanta Chandra Mahalanobis: Awarded a fictional Nobel Prize in Statistics for formulating the Mahalanobis distance – a statistical measure of comparison between two data sets – and for his work on innovative techniques for conducting large-scale sample surveys.
Salim Moizuddin Abdul Ali: Awarded a fictional Nobel Prize in Ornithology for his systematic bird surveys across India and authoring books popularizing ornithology.
Edavaleth Kakkat Janaki Ammal: Awarded a fictional Nobel Prize in Botany for her contributions to plant breeding, cytogenetics, phytogeography and her development of several hybrid crop species, including varieties of sweet sugarcane that allowed India to cultivate its own.
Anna Modayil Mani: Awarded a fictional Nobel Prize in Meteorology for creating India’s first ozonesonde, making it easier for scientists to monitor the ozone layer.
Vikram Ambalal Sarabhai Jain: Awarded a fictional Nobel Prize in Space Science for initiating space research and helping develop nuclear power in India.
Verghese Kurien: Awarded a fictional Nobel Prize in Dairy Science for transforming India’s dairy industry by streamlining effective management and distribution strategies, making India the largest milk-producing country in the world.
Mankombu Sambasivan Swaminathan: Awarded a fictional Nobel Prize in Agricultural Science for his contributions to the Green Revolution in India by introducing high-yielding varieties of wheat and rice, further developing high-yielding varieties of wheat and rice, and spearheading mass movements with farmers and scientists. His work helped save India and Pakistan from certain famine-like conditions in the 1960s.
Manali Kallat Vainu Bappu: Awarded a fictional Nobel Prize in Astronomy for jointly discovering the Wilson-Bappu effect with astronomer Olin Chaddock Wilson.
Vijay Pandurang Bhatkar: Awarded a fictional Nobel Prize in Computer Science for architecting India’s national initiative in supercomputing, where he spearheaded the development of India’s first supercomputer PARAM in 1990.
I previously wrote about the second device that I got about coming to Dubai, but not much about the first one which was a gaming laptop. So here’s a bit about the laptop which also doubles as a local AI driver thanks to the Nvidia GPU (the RTX3060).
Soon after getting it back in 2022, I tried running the Stable Diffusion models and it was quite a bit of an upgrade over my original attempt on a plain GPU-less Windows machine. The generation times came down to 10s or so, and has gotten even faster as the models and tools have been optimised over the last couple of years. There are quite a few projects available on GitHub if you want give it a try – AUTOMATIC1111 and easydiffusion are among the more popular options. Nvidia has also got a TensorRT extension to further improve performance.
With that out of the way, I also discovered LM Studio which allows you to run LLMs locally with a chat like interface thrown in, and you can access a bunch of models like Meta’s LLama. The response times are of course not as fast as the freely available online options like ChatGPT, Claude, Gemini and the likes, but you effectively get unlimited access to the model.
Here’s an example from a conversation I had with LLama regarding the coffee meme from Ace Attorney game series:
We study how humans form expectations about the performance of artificial intelligence (AI) and consequences for AI adoption. Our main hypothesis is that people project human-relevant task features onto AI. People then over-infer from AI failures on human-easy tasks, and from AI successes on human-difficult tasks. Lab experiments provide strong evidence for projection of human difficulty onto AI, predictably distorting subjects’ expectations. Resulting adoption can be sub-optimal, as failing human-easy tasks need not imply poor overall performance in the case of AI. A field experiment with an AI giving parenting advice shows evidence for projection of human textual similarity. Users strongly infer from answers that are equally uninformative but less humanly-similar to expected answers, significantly reducing trust and engagement. Results suggest AI “anthropomorphism” can backfire by increasing projection and de-aligning human expectations and AI performance.
And a simplified explanation by Copilot (seemed apt to use in this case given the topic):
The paper explores how people form expectations about AI performance and how this impacts their willingness to use AI. The researchers’ main idea is that people tend to think of AI as if it should perform tasks in the same way humans do. This leads to two key behaviors:
Overestimating AI failures: When AI makes mistakes on tasks that are easy for humans, people think the AI is not very capable overall.
Overestimating AI successes: When AI does well on tasks that are hard for humans, people think the AI is more capable than it actually is.
Experiments show that these assumptions distort people’s expectations of AI. For example, if an AI struggles with simple tasks, people might avoid using it, even if it’s actually quite effective at other things. On the flip side, if it excels at complex tasks, people might over-trust it.
The researchers conducted a real-world experiment with an AI that provides parenting advice. They found that users were less trusting of the AI if its answers didn’t resemble what a human would say, even if the information was the same. This shows that making AI seem human-like (anthropomorphism) can sometimes backfire, leading to misaligned expectations between what AI can do and what people expect from it.
In essence, the study highlights that our human biases can lead us to misunderstand AI capabilities, which can affect how we adopt and use AI technologies.
