Rishabh Chaudhary

AI + Full Stack Engineer building agentic products -

[Rishabh Chaudhary @risbdev]

Best part of Super 30 getting to build with my roommates.

Built BookMyShow from scratch in 4 hours.

No AI usage. Just us.

[Nikhil Kamath @nikhilkamathcio]

Every prompt you send ends at a chip. That chip costs more than the building and the land combined.
Companies lease because owning sinks returns. Countries can't think that way. They need jurisdiction, not hardware.
Rent what depreciates.
Own what endures..
So who actually owns AI infrastructure - the companies renting it out, or the countries that can't afford not to control it?

[Rishabh Chaudhary @risbdev]

Microservices database design is way more complex than I thought.

Time to research more on this one.

The brainstorming journey continues.
@dhruuuvv__

[Naval @naval]

Open-source AI models do not threaten frontier lab profitability.

The most valuable sectors of the economy - investing, product development, war, cybersecurity, even scientific discovery - are adversarial and competitive in nature.

You pay to win, or someone else will.

[Sam Altman @sama]

astra is a powerful model and we are working to make it generally available.

we do not think it is a good strategy to keep powerful models to a chosen few.

given its cyber capabilities, we need a little big longer to do do this safely. but hopefully not too long!

[Naval @naval]

The hierarchy of desire:
- The fame
- The money
- The team
- The product
- The work itself

[Sundar Pichai @sundarpichai]

I also want to give a huge thanks to the incomparable @JeffDean after an incredible 27-year run at Google. He’s off to start his own public benefit corporation with @Sanjay_Ghemawat focused on accelerating discoveries across ML, science, & engineering. @Google will support as a founding investor and Cloud partner. On a personal note, it’s been a privilege to work with Jeff and Sanjay, and I wish them all the best. Thank you for everything!

[Rishabh Chaudhary @risbdev]

https://t.co/3TLkq1ui4G

Here's the architecture diagram of a quick commerce application.

[Rishabh Chaudhary @risbdev]

Distributed systems get messy as they scale.

White-boarding the HLD of a quick commerce application

[Rishabh Chaudhary @risbdev]

Nothing fancy.
Just a white board and Blinkit’s architecture

[Rishabh Chaudhary @risbdev]

@arpit_bhayani The future belongs to the curious.

[Rishabh Chaudhary @risbdev]

@akshaymarch7 Yes please 🙏🏼

[Naval @naval]

Agent Programming Interface.

[Rishabh Chaudhary @risbdev]

Ending the day with a microservices payment flow.
Architecture diagram 👇

[Andrej Karpathy @karpathy]

We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does anything at all.

I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free". There might be a lot more. But I'm excited about creating hyper custom worlds that you can imagine dropping players into, e.g. here to participate in the LoTR story as a spectator NPC, or one of the characters, or etc. Something like an ephemeral GTA of X on demand.

Last thought is that the domain of worlds/games exposes a weakness in LLMs: they can't easily audit their work because they aren't able to efficiently and natively perceive videos or play games within them. Here, Opus 5 had to very slowly and painstakingly take screenshots at different points, and it messed up a few times and created a bunch of jank. An example of raw capability (multimodal, gameplay) that I think is still quite lacking.

[Rishabh Chaudhary @risbdev]

Just finished reading this article on syncing databases in microservices.

Didn't realize system design was this deep. Every topic opens the door to five more.

#SystemDesign #Microservices #DistributedSystems

[Arpit Bhayani @arpit_bhayani]

Getting the feeling that companies now are not as bullish or as aggressive about AI as they were a few months ago.

Looks like the following things have compounded enough and have gone out of bounds.

- unnecessarily sloppy code
- unreliability in systems
- rising token costs
- agents breaking outside happy paths
- products not delivering enough value

Markets being this volatile and engineers not caring enough about systems is not helping either.

Companies might be realizing that AI is a great assistant and aid, and that the narrative around it replacing "everything" was an oversell and an overestimation.

Or maybe I am reading it all wrong :)

[Sam Altman @sama]

cool use case of chatgpt work i heard last night:

connect your family calendars and explain your kids' interests.

every morning for the drive to school, have it make a podcast that talks about one kid's soccer game that afternoon, one kid's upcoming birthday, some news, etc.

[Hubert Thieblot @hthieblot]

It’s time to get more aggressive about the company you want to build.

[Pri @solopribuilds]

Nobody talks about Al hallucinating anymore.

Why?