What Are Embeddings and Why They’re Incredibly Useful
Published:
If you’ve heard of the term “embeddings” before but don’t quite understand it, this post is for you. I’ll provide an intuitive explanation of embeddings and their significance.
Blog posts
2024
6 Questions To Scope Business Requirements Before Starting a Data Science Project To Improve Success
Published:
When there is a data science problem to solve, my instincts are to start coding and build something impactful with the latest technologies. However, I’ve learnt the importance of slowing down and taking the time to ask “Why?” to understand the root business problem from the stakeholders’ perspectives.
Traditional Natural Language Processing (NLP) Tasks: Understanding What Large Language Models (LLMs) Can Do For You
Published:
Since Transformers were introduced in 2017, Natural Language Processing (NLP) capabilities have skyrocketed. Knowing traditional NLP tasks is useful to understand the capabilities of (Large) Language Models. Although LLMs may outperform in many areas, smaller fine-tuned models will always have a place due to their faster latency and lower costs.
5 Tips I’ve Learnt to Build My Professional Network in a New Country with Zero Connections
Published:
Moving to Singapore with zero connections, I faced the challenge of building a professional network from scratch. Networking can change your career trajectory, leading to opportunities you might never have encountered otherwise. Here are five tips I’ve learned to make networking more enjoyable.
How AI Assistants Learn: The Training Process of Large Language Models
Published:
Understanding the training process of AI assistants reveals how they evolve from simple language models to sophisticated, useful tools. Here’s a breakdown of the stages involved.
Prompting Tips for Better LLM Outputs
Published:
Large Language Models (LLMs) are complex probabilistic machines that predict the next word. Prompt engineering is about conditioning them for desired outputs. Each instruction steers the model’s generation. Here are tips to prompting LLMs to generate useful outputs to your problems.
Simple Tips to Read More Books This Year
Published:
Reading is a great habit that can expand your knowledge, spark creativity, and be inspired by others. I read an average of six books each year these past six years. This year, I’ve made a conscious effort to read more and learned some tips. I’ve currently read twelve books over the past six months.
Day 4: How I Switched Careers From Mechanical Engineering to Data Science
Published:
In this post, I’ll share how I transitioned from mechanical engineering to data science in 2020 while working full-time.
Day 3: How Writing Online Landed Me Freelance Work Despite a Tough Job Market
Published:
In today’s tough job market, especially in the competitive data science field, writing online and building a personal profile helped me stand out and find freelance work.
Day 2: Why I Moved to Singapore Jobless, Leaving Behind My Free Data Science Degree
Published:
Last year, my partner and I made a life-changing decision to uproot our comfortable lives in London and move to Singapore. We’d never been there before and had no connections.
Day 1: Why I’m Building a Daily Online Writing Habit
Published:
I recently signed up for Dickie Bush & Nicolas Cole’s cohort-based course, Ship 30 for 30.
How I Stay Up-To-Date On The Latest AI Advancements Without Feeling Overwhelmed
Published:
Keeping up with the latest breakthroughs and industry trends can feel like an endless pursuit, leading to information overload.
How Raycast Transformed My MacBook Workflow
Published:
As knowledge workers, the tools we use and how we integrate them into our workflow can greatly impact our productivity, minimise context switching and distractions, and improve overall work experience.
50+ Open-Source Options for Running LLMs Locally
Published:
In my previous post, I discussed the benefits of using locally hosted open weights LLMs, like data privacy and cost savings. By using mostly free models and occasionally switching to GPT-4, my monthly expenses dropped from 20 USD to 0.50 USD. Setting up a port-forward to your local LLM server is a free solution for mobile access.
Why I Use Open Weights LLMs Locally
Published:
As someone who regularly uses Large Language Models (LLMs) for personal use and builds apps with LLMs - the choice between self-hosted open weights LLMs and proprietary LLMs is a recurring theme. Here, I share my personal insights as to why I use locally hosted LLMs. As a disclaimer, I still use ChatGPT’s GPT-4 and GitHub Copilot for certain use cases and have not completed weaned off them yet.
2023
Future of Compute from Jensen Huang, NVIDIA CEO
Published:
I had the pleasure of attending a keynote by Jensen Huang, NVIDIA CEO, hosted by ATxInspire Singapore. Below are a few highlights from a leader who has profoundly influenced our technological landscape:
H2O Singapore GenAI Day
Published:
I recently attended H2O.ai’s Singapore GenAI Day, a fantastic event showcasing their latest contributions to GenAI. Highlights included:
Unpacking OpenAI’s Dev Day: A Leap Forward in AI Development
Published:
OpenAI’s recent Dev Day announcements, such as the launch of GPT-4 Turbo, custom GPTs, and the GPT Store, are going to cause a massive disruption to not just the AI landscape of applications and services but also millions of businesses around the world - by making these powerful tools more accessible.
Decoding Kaggle’s 2023 AI Report: Essential Tips for Machine Learning with Tabular Data 🔍📈
Published:
It’s difficult for us to stay on top of the latest AI advancements with 100s of research papers, articles, and newsletters published daily. Luckily, Kaggle has recently published their annual AI report earlier this month, which distills and summarises the latest advancements this past action-packed year.
🔍 Unmasking the Unusual: An Intro to Anomaly Detection
Published:
In this beginner-friendly post I’ll introduce the concept of anomaly detection, also known as outlier detection, focusing on the popular technique of density estimation. This introductory guide is the first post of a mini series of 3 posts, where in upcoming posts I’ll share the most cutting-edge anomaly detection methods used across industries.
🎉 One Month in Singapore’s AI Scene 🤖
Published:
It’s been an action-packed first month in Singapore for me, settling into the new country and immersing myself in the vibrant AI community here! Here’s an overview of what I’ve been up to and my main takeaways from 24 hours of meetups and conferences on Generative AI, Machine Learning for finance, and Data Engineering.
Hello and Welcome! 👋
Published:
Thanks for stumbling upon my website. I’ve decided to finally share my thoughts and learnings online to hopefully add value to any readers out there. This space will primarily focus on data science, machine learning, AI, and my experiences living abroad in Singapore.