Gillan 💭

ML @ RBI | Building Digital Public Infra against frauds for 🇮🇳 | TinyML enthusiast |

Opinions are my own

[Gillan 💭 @gillan_data]

@Hi_Mrinal Checkout MLE Path and ML Tech lead if youre into ML too

[Gillan 💭 @gillan_data]

@pHequals7 ROFL

[Gillan 💭 @gillan_data]

@Ayussheth +1

[Gillan 💭 @gillan_data]

@manthanguptaa Would be interesting to see how you deal with a cold start!

[Gillan 💭 @gillan_data]

@manthanguptaa Happy birthday bruv!

[Amit Shah @AmitShah]

The banking sector should adopt the mule hunter software built by the Govt. of India and RBI and sanitise their systems.

[Manthan Gupta @manthanguptaa]

Had the first tech meetup today in collaboration with Bangalore Newbies Community (link in comments)

Loved nerding out on different aspects of tech. Look out for the next one!

[Gillan 💭 @gillan_data]

@manthanguptaa Likewise. Fun sunday!

[Reserve Bank Innovation Hub @rbinnovationhub]

Leadership update 📢

We welcome Mr. Mujiruddin Shaikh as Chief Technology Officer at Reserve Bank Innovation Hub.

With 27+ years of experience across banking, retail, and healthcare, he will lead data and engineering, building population-scale DPIs.

[Arpit Bhayani @arpit_bhayani]

I never understood the need for a granular planning of projects.

You know something needs to be done, you make your rough estimates, and then you run with it. Once ready, you roll it out. So long as engineers are motivated to do it, they will run with it.

But spending weeks breaking down tasks to the most granular level, deciding efforts, and going back and forth on timelines for every single one of them is such a waste of engineering energy and bandwidth.

This energy could have been easily used to build things. Every extra hour spent polishing timelines is an hour not spent moving the product forward.

Let engineers code. Tell them the impact of their work. That's all it takes.

[Manthan Gupta @manthanguptaa]

I spent the last few days prompting Claude to understand how its memory system actually works, and it's completely different than ChatGPT's approach

Spoiler alert: There is no vector database used

https://t.co/vc7FNaq1FR

[Gillan 💭 @gillan_data]

@Samiksha2908 Google sites for text/graphs, streamlit/gradio for live demos

[Pankaj @the2ndfloorguy]

story behind "why netflix built https://t.co/YDCurkt2BM" is brilliant.

so, netflix had a massive fight with ISPs around 2014-2016. ISPs were slowing down netflix on purpose. they wanted more money from netflix

customers got bad streaming. but ISPs just blamed netflix.

netflix had to pay comcast, verizon, at&t and time warner for direct connections to their networks.

but in 2016, they launched fast dot com, clever part - It's not testing your general internet speed. It's testing your speed to netflix's servers specifically. so when someone complained about buffering, netflix could say "run fast dot com." If it's slow, the ISP is the bottleneck.

suddenly millions of people had a tool to prove their ISP was the problem
ISPs couldn't hide anymore.

netflix positioned themselves as the transparent good guys fighting for customers while ISPs looked like greedy monopolies

they solved a pr problem and a customer service problem with one simple website

I guess, that's how you win a corporate war

[Satyam @sattyyouneed]

The side of Karpathy nobody talks about
@karpathy

-> left OpenAI twice, sparking speculation about internal disagreements
-> walked away from one of the most powerful AI jobs in the world
-> took criticism when Tesla Autopilot faced public pressure and accidents news
-> carried responsibility for technology where failure could cost real human lives
-> faced burnout from nonstop high intensity engineering culture
-> chose principles over prestige, even when people thought he was crazy
-> rejected huge salaries to reset and rebuild his mind
-> stepped out of the spotlight when most would chase fame
-> got judged harshly online for decisions nobody knew full context about
-> took career risks when everyone expected him to play safe
-> said “no” to power to protect creativity and sanity
-> left elite institutions to start from scratch again
-> fought against the idea that success means titles and money
-> openly talked about struggling with focus and needing solitude
-> kept working while people doubted his choices and direction

[Gillan 💭 @gillan_data]

@VTikke 4 years in this field and Im still learning.

[Gregory Kennedy @gregorykennedy]

Dave: "Masa Son, welcome to the show. What's going on?"

Masa: "Dave, I sold my entire NVIDIA position."

Dave: "How much?"

Masa: "All 32.1 million shares. $5.8 billion."

Dave: "And why did you do that?"

Masa: "To go all-in on AI."

Dave: "You sold your NVIDIA stock... to invest in AI."

Masa: "Yes."

Dave: "NVIDIA makes the chips that run AI."

Masa: "Correct."

Dave: "So you sold the shovels to buy lottery tickets."

Masa: "I prefer to call them 'high-conviction bets.'"

Dave: "Got it. And this is your second time selling NVIDIA completely."

Masa: "That's right."

Dave: "In 2019, you sold $4 billion worth."

Masa: "Yes."

Dave: "Which would be worth $150 billion today."

Masa: "I'm aware."

Dave: "So you already missed out on $146 billion from the first sale."

Masa: "When you say it like that—"

Dave: "And now you're doing it again. To put $30 billion into OpenAI."

Masa: "And a $1 trillion AI manufacturing hub in Arizona."

Dave: "Right. Because WeWork worked out so well."

Masa: "That was a stain on my life, Dave."

Dave: "Cost you $11.5 billion in equity losses. Plus another $2.2 billion in debt."

Masa: "Adam and I fell in love."

Dave: "You fell in love with a guy who wanted to trademark the word 'We.'"

Masa: "He had vision."

Dave: "And before that, you lost $70 billion in the dot-com crash. The largest personal loss in history."

Masa: "But then I made it back with Alibaba."

Dave: "After a six-minute meeting."

Masa: "Jack Ma is very persuasive."

Dave: "So your entire investment strategy is falling in love during short meetings and then losing generational wealth."

Masa: "I believe in the singularity."

Dave: "Right. So just to recap: you've lost $70 billion, missed out on another $146 billion, burned $13.7 billion on WeWork, and now you're selling NVIDIA at what might be the worst possible time to bet it all on Sam Altman."

Masa: "Sometimes you have to push all your chips to the center of the table."

Dave: "You've done that four times and lost three of them."

Masa: "But that one Alibaba win though."

Dave: "Okay. Thanks for calling in."

[Gillan 💭 @gillan_data]

@pHequals7 Did you mean: Bob?

[Eddy Xu @eddybuild]

today, we’re open sourcing the largest egocentric dataset in history.

- 10,000 hours
- 2,153 factory workers
- 1,080,000,000 frames

the era of data scaling in robotics is here. (thread)

[Gillan 💭 @gillan_data]

@DevanshuXi Competing for a participation trophy

[Gillan 💭 @gillan_data]

@pHequals7 Ph and pk goated combo back in the day