[8th September 2024] Interesting Things I Learnt This Week

1. A Single Gold Bar Is Worth $1 Million for the First Time in History - It discusses why the price has gone up and what this means for the future. The price of a single gold bar has recently reached $1 million for the first time ever. This is because gold is seen as a safe investment during times of economic uncertainty. The article predicts that the price of gold will keep going up.

My Take: Gold has always been seen as a safe investment in India. We have seen the Gold Bond which were introduced by Government of India which has become too popular to be supported by GoI. E-Gold is a safe way to keep gold especially since for folks who are buying to for purely investment purpose and not holding black money in India. I hope that the space becomes more reliable and competitive. Though folks would say that Gold does not give the best returns always, which is true but the fact also is that it provides safety in terms of investment unlike stock market, at least till we are able to create artificial gold. Till then it will remain a valuable investment.


2. Buy Experiences instead of Possessions to Build Social Connection - Shared experiences, more than material things, bring people together

My Take: I guess this is a no-brainer but we are too consumed into buying the next more exclusive and expensive stuff. Think about it: A new pair of shoes might provide a temporary boost, but a weekend trek in the Western Ghats or a cozy evening at a local café with friends creates lasting memories and shared stories. These experiences become a part of your identity, something you can talk about and connect with others over. Experiences over possessions can lead to deeper connections, more meaningful memories, and a richer life.


3. TalkBack uses Gemini Nano to increase image accessibility for users with low vision - Google’s TalkBack uses Gemini Nano to increase image accessibility for users with low vision. It discusses what TalkBack is and how it is always working to make Android more accessible.

My Take: I guess this is one of the better uses of LLMs. With we still struggling to get applications compliant to various standards of accessibility standards. So many of them, even those by governments are not accessible. Not that building accessible apps is not required, but this provides a catch all tool which can make lives of people with visual impairments better. I imagine having smart glasses which relay the current real life visual in an auditory format for people with challenges would really be game changer in many ways.

 

4. Building LLMs from the Ground Up -This YouTube tutorial provides a comprehensive introduction to large language models (LLMs), covering their inner workings, implementation in PyTorch, and practical applications. It begins with an overview of LLMs, their recent advancements, and various use cases. The tutorial then guides viewers through the process of building a small GPT-like LLM from scratch, including data input, architectural components, and pretraining. Once the model is built and trained, the tutorial demonstrates how to load pretrained weights and fine-tune it using open-source libraries.

My Take: I have not gone through this tutorial completely. But its topics are very interesting. Anyone who is interested in learning about architecture of LLMs, pretraining and fine tuning, this is a great place to start. This should probably be part of engineering curriculum and every AI enthusiast should understand these concepts very well and not be just limited to art of prompt engineering.

Comments

Post a Comment

Popular posts from this blog

[24th November 2024] Interesting Things I Learnt This Week

Image
1. AI Makes Tech Debt More Expensive - The core argument is that generative AI significantly widens the gap between codebases with low and high tech debt. Companies with clean code can leverage generative AI to write code much faster, while companies with messy legacy codebases struggle to adopt these new tools. This widens the gap between the two codebases, making tech debt even more expensive for companies with outdated systems. My Take : Legacy systems inevitably accumulate technical debt. A common analogy for this is the state of urinals over time: missed targets lead to increasing mess, keeps pushing people away from urinals and leading to more mess in turn. AI-powered coding tools could potentially accelerate the accumulation of tech debt. However, skilled engineers can leverage AI to reduce and even eliminate it. Ultimately, AI is just a tool, and human judgment remains crucial for making informed decisions. I hope AI will be used responsibly to drive positive outcomes. 2. Make...
Read more

[17th November 2024] Interesting Things I Learnt This Week

Image
 1. Booleans are a trap : Booleans, while seemingly simple, can introduce complexity and limitations into domain modeling. When used to represent complex states, booleans can lead to unclear code and potential errors. To avoid these pitfalls, consider using enums or enum sets. These approaches provide a more expressive and maintainable way to model complex states in your applications. My Take : I wish I had learned this earlier in life. When working with Google Docs, I realized the limitations of booleans. Expanding boolean-based behaviors often led to adding more fields, making the system complex. Enums would have provided a simpler solution. The problem wasn't just the booleans themselves, but also the need to pass them through multiple layers of the stack, often requiring additional parameters. Another important aspect of enums is the inclusion of an " enum not specified " state. This state explicitly indicates that an enum value hasn't been set, which can be usef...
Read more

[1st December 2024] Interesting Things I Learnt This Week

Image
1. C++ Pitfalls - this article, explains some of the pitfalls you can fall into when programming in C++ and shares their experience with them. This includes Operator precedence, Arithmetic conversion rules, Right bit-shift, Implicit conversions and Order of evaluation.  My Take : We've all read about JavaScript's quirks, leading to unexpected outputs. But let's remember that such behaviors aren't unique to JavaScript. Even languages like C and C++ have their share of ambiguities and compiler-specific behaviors. While it's tempting to dive deep into these intricacies, I've found that focusing on clear, consistent, and unambiguous code is often more practical. However, understanding these nuances is essential for any experienced programmer. It helps us avoid pitfalls and write robust, reliable code. Remember, mastering a language isn't just about writing "Hello World." It involves delving into its intricacies, including its counterintuitive and ambi...
Read more