Prashanth N

Aspiring entrepreneur | start up, web, ai enthusiast | commerce graduate turned coder | JS enthusiast | learning nodejs | looking for a job

[Prashanth N @I_amPrashanth]

@DrinkPrime please help in disconnecting the service. I have raised a request and it’s been 4 days and your support is useless and helpless. One support agent name Abel is asking to wait and have no answers.

[Prashanth N @I_amPrashanth]

@holy_photon And still i ended up getting fake item.

[Prashanth N @I_amPrashanth]

@soorajchandran_ That’s one good Malayalam film!

[shadcn @shadcn]

New components. This time it’s the boring stuff. The things we rebuild over and over. Made into components.

Button Group, Field, Input Group, Empty States, Item.

They compose beautifully and handle the common patterns we reach for every day.

Let’s take a look ⬇️

[(fan) Frank 🧠🇾🇪 @FrankEra_]

During pre-season, a Sporting Lisbon fan reached out to me with confidence that Ruben Amorim would turn it around at Manchester United, highlighting his ability to turn a squad into fighters, a family.

I reached out to him today, asking him whether he was surprised about Amorim's stubbornness at United so far, shown through his inability to show any adaptation to his ways of playing football.

Here was his response:

"Hey Frank, I hope you are well. I am not shocked, even though I never thought it would be so hard for him to have the players doing the basics – but I knew it would be hard.

"Forget the stubbornness, that shouldn’t be your concern. Amorim changes a LOT in his teams – so many times last year we had just 2 in the back, or one of the centre backs going forward and acting like wingers, or one of the midfielders opening on a side to allow for one of the centre backs to go forward. He changes a lot but only once he sees the team are very comfortable with the basic patterns.

"The problem, though, is not this. I’ve said this after Grimsby, he gave up. He sees a team that can only be aggressive in big matches as Arsenal or Chelsea. I know him well and he said everything after that match – he feels he is not capable to make the team understand that they have to give everything in every single match, every little detail. So he gave up.

"I am absolutely confident that, if you guys sack him, he will have a lot of success elsewhere. He has a winner profile and knows a lot about football. The only mistake we’ve made (him and fans that know him well as I do) was to believe that he could make a team out of any group of players. He can’t. And I really can’t see who can make a team out of these United players.

"I don’t know United that well to be able to point the reason why this weak mentality is so prevalent there – I’ve been following Sporting every day for the last 27 years, it’s not the same with United. But I can tell it runs deep in the club. Too many years of bad football heritage.

"Also, you guys have a fanbase that is still not ready to accept being a mid-table team for a couple of years, but that’s what you guys are now.

"Little details (literally two penalties) would have put you in the 7th place now with Man City, but the fanbase is not ready to have the little details go wrong for long.

"Manchester United is huge, but history doesn’t win games and the size of the fanbase doesn’t win titles.

"I don’t think (at all) that he is setting you guys up to lose. I hate Dalot and even I think he should be able to know how to do the basics. Just as I love Bruno and I think he should be able to manage his emotions during the match. There are just too many little things to change. With no time to change them."

[Prashanth N @I_amPrashanth]

@rohanpaul_ai @cryptocopypro true!

[Yin Yang Launcher @YinYangLauncher]

🧘‍♂️ Introducing Focus Mode
Choose what deserves your attention.
Only the apps you need — nothing more.
Stay clear. Stay focused.

🎥 Watch it in action: https://t.co/HEKmHhw8V9

#FocusMode #DigitalDetox #AndroidLauncher #MindfulTech #YinYangLauncher

[Rolet Oliver Fernandes @roletoliver]

You tap Instagram "just for a minute" and suddenly 30 minutes are gone.

Sound familiar?

Here's how a simple 5-second pause can break this dopamine cycle 🧵

[Rolet Oliver Fernandes @roletoliver]

I've been building Yin Yang Launcher solo for 16 months. This is the biggest update yet — a complete rebuild over the last 6.

🧘 Minimal. Mindful. Designed to help you use your phone with intention.

📲 https://t.co/sXRZErZnto

#MinimalistLauncher #DigitalWellness #IndieDev

[Prashanth N @I_amPrashanth]

@ManUtd Football, bloody hell. ❤️

[Prashanth N @I_amPrashanth]

@ManUtdBangalore Football, bloody hell. ❤️

[Manchester United @ManUtd]

This is your future.
Your home.
Your United.

#MUFC

[MUSC - Bengaluru @ManUtdBangalore]

February 21st, 1958!
OTD, we lost the greatest of all, Mighty Duncan Edwards🥺 #duncanedwards After battling for 15 days from injuries of Munich air disaster.
@ManUtd
Unfortunately our generation isn't lucky enough to watch him play live, but legends say he was out of the planet

[MUSC - Bengaluru @ManUtdBangalore]

A broken plane
A broken dream
A broken heart
A broken team
No word said
A silent vow..
We loved you then, we love you now❤️
.
Lest we forget, gone but never forgotten.
We know you're watching upon us from heaven.
Flowers of Manchester, Flowers of English Football
.
#busbybabes

[Andrej Karpathy @karpathy]

New 3h31m video on YouTube:
"Deep Dive into LLMs like ChatGPT"

This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology", and how to get the best use them in practical applications.

We cover all the major stages:
1. pretraining: data, tokenization, Transformer neural network I/O and internals, inference, GPT-2 training example, Llama 3.1 base inference examples
2. supervised finetuning: conversations data, "LLM Psychology": hallucinations, tool use, knowledge/working memory, knowledge of self, models need tokens to think, spelling, jagged intelligence
3. reinforcement learning: practice makes perfect, DeepSeek-R1, AlphaGo, RLHF.

I designed this video for the "general audience" track of my videos, which I believe are accessible to most people, even without technical background. It should give you an intuitive understanding of the full training pipeline of LLMs like ChatGPT, with many examples along the way, and maybe some ways of thinking around current capabilities, where we are, and what's coming.

(Also, I have one "Intro to LLMs" video already from ~year ago, but that is just a re-recording of a random talk, so I wanted to loop around and do a lot more comprehensive version of this topic. They can still be combined, as the talk goes a lot deeper into other topics, e.g. LLM OS and LLM Security)

Hope it's fun & useful!
https://t.co/75mXcUBI8L

[Prashanth N @I_amPrashanth]

@ManUtdBangalore looking to attend the screening of the next match, can you please dm the details?

[Prashanth N @I_amPrashanth]

Are you tired of scrolling endlessly on your phone?
Failed miserably in controlling the screen time?
Now is the time to take the control of your life back. Try out yinyang launcher,
A perfectly balanced launcher where you control your phone.

https://t.co/ajbsO8zBqQ

[Prashanth N @I_amPrashanth]

Current mid life crisis: supporting Manchester United. 😐😕

[Prashanth N @I_amPrashanth]

@F1 Leave me alone. I know what am doing

[Prashanth N @I_amPrashanth]

@UtdFaithfuls Looks weird with the hair. Am i the only one? 🫣