It was quick and this was my prompt:
A memorable repetitive beat that can be danced to that sounds like house music with a rap beat. suitable for studying. Instrumental only.
#Gemini #GoogleAI #Multimodal #AudioAnalysis #AI #BerniePng #TechTrends #Productivity #LLM #Gemini15Pro #AITesting #FutureTech #VoiceAI #MachineLearning #Innovation
I’m discovering that the reason why we can create and do stuff so efficiently is as much the effort of AI as it is human effort.
Without the huge repository of human creation through the centuries (the inventors, the artists, the philosophers), AI wouldn’t have a chance to synthesize our knowledge to help the rest of us (the common folk).
AI just made knowledge and creativity more accessible.
But we still need the human geniuses among us to create and innovate. Our imagination needs to prevail for the future of humanity.
That is our value.
Only then, can we work side by side, and not behind, AI.
On a side note, we should re-think how to protect human creativity. Current copyrights and trademark laws need to be revamped.
What do you think? (I'm asking the humans) :)
#AI #HumanAICollaboration #FutureOfWork #HumanCenteredAI #ArtificialIntelligence #Innovation #DigitalTransformation #HumanTouch #AITrends #BerniePng
March has been crazy. Everyday I'm bombarded by AI news – launching of new LLMs, new Claude features, a better way to do things, combining this to that, datacenters sprouting up here and there – and even for someone who loves change, the velocity of AI changes is honestly hard to keep up.
I'm (still) loving every bit of it, and my brain is on fire. Check in on me in 2 months, I might have a different story to tell. Might be fried by then.
Three key mini inflections took place in my life with AI this month:
1st week of March
2nd week of March
3rd week of March
At some point in the keynote Jensen said that in the future we would not just be paid in money, aka salary, but also, with tokens. I believe him. But what does it mean for us, the common folk? He talked about AI factories and showing off all his highly efficient racks with awesome “tokens/watt” servers, and how everything will be opensource. It's like “here's all the free chocolate and candy you can eat, but you have to pay for the teeth.”
Welcome to the new world.
What would a truly localized Singaporean LLM look like? Beyond just Singlish, I explore how a 'fellow citizen' AI could navigate our unique cultural nuances.
As I'm going through the free Stanford Online course CME295, I thought about Natural Language Processing (NLP) and how we currently tokenize English text to feed into LLMs. If we transform words into numbers, how do we add in culture nuances, slangs, etc that are unique to a country so that we can create a sort of naturalized citizen? What is Singapore currently doing?
So I asked Gemini for some thoughts:
so if I am a citizen of a country who wants to help build a realistic LLM for my country where we have 4 languages and we want to not only create a balanced LLM, but also to incorporate our country's culture and slangs into it so that the LLM performs like a "fellow citizen" and knows all our nuances and history. How should I start?
Gemini's answer: “This is a noble and technically fascinating mission. Building a “Sovereign LLM” is the move from a model that knows about your country to a model that is of your country.
To make an AI feel like a “fellow citizen,” you have to move beyond just scraping the web. You need to follow a four-stage blueprint:
...
Be careful with “Data Poisoning.” If you only scrape one political side or one ethnic group's slang, your “Fellow Citizen” AI might end up being biased or exclusionary. Balance is your hardest job.”
It then went on to suggest some open-source models to start with and actionable next steps.
[NOTE] I'm using this blog article to document the start of my journey. It will be a multi-year quest of mine. I know Singapore is already embarking on building her own LLM or LLMs, but wouldn't it be great if I can create my very own Singaporean friend, a super knowledgeable, kind and caring one at that.
Cool idea?
#ai #LLM #NLP #SovereignAI #Singapore #Singlish #AISingapore #CME295 #LearningInPublic
Can a solo-builder contribute to Singapore’s national AI mission? I’m pursuing an AI Singapore apprenticeship to help transform our local talent into a global export.
I recently had a realization while watching Dispatches from Elsewhere: staying quiet is a form of selfishness. In the show, Fredwynn tells Peter that by not sharing his perspective, he’s withholding something valuable from the group. That hit home. For too long, I’ve been a quiet solo-builder, but as I pursue an apprenticeship with AI Singapore (AISG), I’ve realized that my mission, and the knowledge I gain, belongs to the community.
Singapore has no natural resources; we only have our people. I believe AI is our unique opportunity to transcend our physical limits and export local talent to the world. To get there, I’m attacking this from three angles: building real-world solutions, earning technical certifications, and finally, refusing to be 'selfish' by sharing every step of this journey in public.
If I don't get the apprenticeship I will still keep building.
Thanks for reading.
#reflection #ai #apprenticeship #AISingapore #AISG #SingaporeTech #SoloBuilder #AIGovernance #SmartNation #CareerPivot #LearningInPublic
After two months of diving into machine learning, I’ve realized that data science is like performing an autopsy on a business problem to find the clues hidden in the facts. By treating data like a detective mystery, we can stop guessing and start building solutions based on real-world evidence and predictive confidence.
At the start of 2026, I jumped head first into the world machine learning (ML) and data science (DS), and I realized that I'm starting to look at the world with a new lens, and add-on if you will, where every problem starts with data.
I know, some of you reading this might say “no Bernie, we always start with identifying the business problem, and ask ourselves what are we trying to solve.” Yes, that too, but after that, you would hire a data scientist right? That's where I'm starting my story.
The clues are in the data. With every business problem, the data is like a dead body on an autopsy table, ready for the data scientist to slice and dice, looking for clues as to why there's a problem in the first place. I've always loved a good detective and/or medical drama, and now I know why. ML and DS is also like that. Find the clues, solve the mystery. And after we solve the mystery we can start building a solution based on facts, which can then point us into the right direction to collect, not just more data, but the RIGHT data. Ultimately we would like to be able to predict with higher confidence, the consequences of our future decisions and actions, so we don't make the same mistakes that would cause said problems to arise again.
So many examples from the real-world, like
It can help us create systems and processes for better business ROI.
I've always wondered about such things. Why are things the way they are. Almost everything we see around us is a consequence of someone's decision and action – what made that person come to that choice? And by understanding their motivations (through the data) we can make better decisions for a future that we want, whether good or bad.
With the right and big enough dataset, we can predict (and solve) almost anything.
#ai #data #reflection #MachineLearning #DataScience #BusinessROI
As a self-proclaimed 'financial illiterate,' I used Gemini 3 to build a Python dashboard that tracks the Rule of 40, Altman-Z, and other metrics to find high-growth companies.
I am no good with money and have never really invested in anything other than one piece of property in my life. But I was thinking, is there a way to identify high-growth companies and be able to predict their ability to stay as leaders and invest in them. What would be the benchmarks and metrics to measure their worth on?
So I wanted to try and create a dashboard, which will tell me at a glance a sort of a health-check, whether a particular company is doing well or not.
I chose Gemini 3's thinking model for this. Apparently it “solves complex problems”. But my problem isn't really complex, I just wanted a python script calling an API and visualization using Streamlit.
Here's my starting prompt
what are the key indicators of companies when evaluating their business growth potential and revenue model, and what kind of competitive analysis data should I collect to compare similar companies to separate the winners from the losers
What followed was about 2-3 hours of Gemini and I coding out a script which connects to yfinance to get real-time data, but now I heard that it isn't that reliable. Here's version 1 of the dashboard.
Check it out —> Bernie's Finance Dashboard
On to my next project! Enjoy!
#finance #ai #built #Python #Streamlit #FinTech #Gemini3 #SoloBuilder #DataVisualization #FinancialLiteracy #GrowthMetrics
It's simply mind-boggling that AI developments changes on a daily basis, whether it's “who's built a new app?”, or “new AI model release!”, and “[insert job title here] is obsolete!“, there's never a boring day with AI news. Currently the two podcasts that I'm listening to are:
The AI Daily Brief – provides daily updates on daily AI news. Very current and informative.
AI & I – showcases how people and companies are leveraging AI for their work and personal lives.
Now we code.