Kunal Sangwan

Builder, Founder, currently building Finance Agents, ex Built Piggy - Investment App for Indians, Scaled to 200M AUM, YC S17 Alum

[Kunal Sangwan @nuhbye]

@karpathy Does not comes as unexpected, seems like a natural progression to capture more context and build deeper for more enterprise use cases in future. Lots of people were building around slack to achieve the same thing. Looks like a personal office assistant for everybody is on the way

[Garry Tan @garrytan]

There are two loops in every founder's head.

The autism loop: run your own model to the floor, ignore consensus, hold a thesis when everyone says you're wrong. That makes conviction.

The empathy loop: feel what the user feels, sense what the market wants before it has words. That makes traction.

Most people crank one and starve the other. Pure conviction builds something brilliant nobody wants. Pure empathy builds consensus mush.

PG put the whole job in four words: make something people want. The autism loop makes the something. The empathy loop knows it's wanted. The founder is the bridge.

Most great founders show up dominant in the first loop. That's why they're contrarian enough to try at all. The work is grafting on the second.

There is no place in the world that helps founders make the two loops work together to make great startups than Y Combinator. It is the most gratifying part of our work.

[Kunal Sangwan @nuhbye]

@AlanKLFeng Didn't had much use case for MCP in the current project. Majorly blown away by things(intelligence) Claude is able to achieve, which were still in early stages some months back.

[Kunal Sangwan @nuhbye]

Mind = Blown 🤯, after deeply using claude code for past few weeks for backtesting and trading analysis.

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Pulkit Agrawal @pulkitagrawal]

6 months back, I taught an AI model to generate my own pics for the first time. I was blown away with the results! 🤯

Today, we are bringing this to everyone! #AI

[Code Sherpa @0xCodeSherpa]

🚀 Are you intrigued by @balajis #BitSignal but afraid of buying #Bitcoin while it's pumping and losing value later? 🤔

Well, you can heed to the #BitSignal and also protect your downside.

Here’s how 👇

https://t.co/a95wXCBIm5

[Code Sherpa @0xCodeSherpa]

🤖 🤖What if you could hire a robot to swap your tokens on your behalf? 🤖 🤖

What if this robot could save your txns from MEV attacks?

That’s exactly what TWAMMs do...

Introducing LongSwap: https://t.co/eap363OTF9

[Limitless Life @LimitlessLif3]

@orangebook The secret to life is that you can redefine yourself as many times as you need to, you are under no obligation to stay the same. You can wake up tomorrow & simply decide to move in a different direction with your life.

[Farnam Street @farnamstreet]

Only hire focused people.
Only worry about focused competitors.

[Prof. Feynman @ProfFeynman]

Imagine how much harder physics would be if electrons had emotions.

[Andrew D. Huberman, Ph.D. @hubermanlab]

My top 3 science supported health practices.

1) Morning sunlight viewing. To set circadian rhythm, focus, mood etc.

2) 180-200min of Zone 2 (moderate) cardio per week. Cardiovascular health.

3) NSDR (Non-Sleep-Deep Rest; 10-30min, 3-7X per week). Stress mitigation, cognition.

[obront | eth/acc @zachobront]

SNARKS FOR NON-CRYPTOGRAPHERS

ZK tech is looking like the holy grail for Ethereum scalability and privacy.

But how does it actually work? What kinds of things are provable?

And if it’s working, what’s the barrier to full zkEVMs?

I spent the past few weeks diving in… (1/n)

[Shreyas Doshi @shreyas]

Why do companies with major resources & distribution make products that are mediocre & often fail to reach their potential?

There are a handful of reasons, many of which you already know. But there is one under-discussed reason: Operators Optimizing for Optics

Thread:

[Emilio^ @The3D_]

The hardest part of learning solidity and smart contract development is not the language, the assembly, or the optimizations. It's understanding that any choice you make, any mistake can have unforeseen, potentially devastating consequences. ⬇️

[Drex⚡️ @drex_dsgn]

20 @naval quotes.

An illustrated thread 🧵↓

[Prof. Feynman @ProfFeynman]

It's Okay to say "I don't know!"

There's no shame in that! The only shame is to pretend that we know everything.

[6529 @punk6529]

6529 ~1 month old 🥳

Some of you know me from somewhere else 👀

My views on NFTs in the thread below

[10-K Diver @10kdiver]

1/

Get a cup of coffee.

In this thread, I'll walk you through the basics of Decision Fatigue.

Understanding this can help us improve the quality of our "high value" decisions, while reducing the number of "low value" decisions we need to make.

[Paul Graham @paulg]

Every would-be startup founder should read this thread.