Sanjeev Bikhchandani

Internet entrepreneur and investor

[Millie Marconi @MillieMarconnni]

A British biologist looked at 200,000 years of human history and found that the entire reason humans broke out of poverty was not intelligence, not language, not even agriculture, but one mechanism so simple a 6-year-old could explain it.

His name is Matt Ridley.

He is a zoologist by training, an evolutionary biologist by career, and in 2010 he wrote a book called The Rational Optimist that quietly argued the most important fact about human progress had been hiding in plain sight for the entire history of economics.

Naval Ravikant has been telling people to read everything Ridley has ever written for the last 15 years. The reason is the argument inside this one book.

For 200,000 years, anatomically modern humans walked around with the same brain you have right now. Same skull size. Same neural architecture. Same raw capacity for language, planning, and abstract thought.

For roughly 190,000 of those years, almost nothing happened. Generation after generation lived and died inside the same Stone Age toolkit their great-great-grandparents had used. Then somewhere around 50,000 years ago, the line on the chart of human progress started to tick upward. Then it bent. Then it exploded.

The question Ridley spent years on was the only question that mattered. What changed.

It was not the brain. The brain had been the same for 190,000 years. It was not language, which had existed long before the takeoff. It was not even agriculture, which arrived only 10,000 years ago and was actually preceded by the upward bend, not the cause of it.

What changed was that humans started trading with strangers.

This sounds too small to be the answer. Ridley argues that it is the answer to almost everything. The moment one human exchanged a useful object with another human from a different group, something happened that no other species on earth had ever done.

Two ideas that had developed in isolation came into contact. The flint knapper learned what the spear maker had figured out. The fisherman from the coast learned what the hunter from the forest had figured out. The two pieces of knowledge fused into something neither side could have produced alone.

Ridley calls this ideas having sex. The phrase sounds frivolous and it is meant to. The point is that ideas, like genes, get better when they combine with other ideas from different lineages.

An idea sitting inside one head, no matter how brilliant the head, eventually hits a ceiling. The same idea exposed to ten thousand other ideas does something genes do under sexual reproduction. It mixes. It recombines. It produces offspring nobody planned.

The cleanest proof of this argument is the most uncomfortable case study in the book. Tasmania.

Around 10,000 years ago, rising sea levels cut Tasmania off from mainland Australia. A population of roughly 4,000 humans was now isolated on an island, with no possibility of contact with the rest of humanity. They had the same brains. The same language. The same starting toolkit as their cousins 150 kilometers north. The natural experiment was now running.

What happened next is something no economist or geneticist had ever predicted.

The mainland Australians kept inventing. Boomerangs. Spear-throwers. Fishing nets. Bone needles for sewing fitted clothes. Watercraft with paddles. Their technology compounded slowly across the centuries.

The Tasmanians went the other way. They did not just fail to invent the new tools their cousins were developing. They started losing the tools they already had. Fishing was abandoned within a few thousand years. Bone tools disappeared. Fitted clothing disappeared. They forgot how to make fire from scratch and started carrying lit firebrands from camp to camp instead, relighting their fires from a neighbor's whenever their own went out.

By the time European explorers arrived in the 17th century, the Tasmanians had the simplest toolkit of any human society ever recorded. Their material culture had gone backward for 8,000 years.

The archaeologist Rhys Jones called it a slow strangulation of the mind.

Joseph Henrich at Harvard later proved with formal mathematical models that there was nothing wrong with Tasmanian brains. There was something wrong with their network. A toolkit requires a critical mass of people exchanging skills to maintain itself.

The act of teaching a skill is imperfect. Every generation loses a small percentage of what the last generation knew. If your population is large enough and trading widely enough, those losses get caught and corrected by someone else who still remembers.

If your population shrinks below a certain threshold and stops mixing with outsiders, the small losses compound until entire technologies disappear.

This is the part that should haunt anyone reading this in 2026.

Intelligence is not a property of the individual brain. Intelligence is a property of the network the brain is connected to. A genius in isolation will produce less than a mediocre thinker inside a dense exchange of other mediocre thinkers.

The thing your ancestors needed in order to break out of 190,000 years of stagnation was not better brains. It was better connections between brains they already had.

The implication for any individual is direct and uncomfortable. If you are smart and isolated, you will be outproduced by people half as smart who are connected.

The most successful people in any field are almost never the smartest people in it. They are the ones positioned at the intersection of the most idea flows. They are reading more authors than their competitors. They are talking to more people from more disciplines. They are in the rooms where ideas from different lineages bump into each other.

Ridley ends the book on the line that sounds optimistic but is actually a warning its this "The future will be invented by people who connect ideas, not by people who guard them."

[Veena @veenavenugopal]

For this month's India Brief Q&A, I sat down with Zomato founder Deepinder Goyal, for a feisty and sometimes confrontational exchange
https://t.co/9RBTf9W3wg

[Sanjeev Bikhchandani @sbikh]

A few weeks back I had spoken at the Launch of the book “The Business of Business is (not) just business : How Behavioural Tools Can Drive Real Change” written by @sutapaban published by Harper Collins.
The session was moderated by Safi Rizvi and Sutapa and I were panelist’s.
I was reminded of this when I just saw a piece in The Print about it

https://t.co/xTPTzipMNC

The book is full of insights about how knowledge of human behaviour gives insights that can influence and drive businesses and business strategy.
In my chapter in this book I discuss how observation of my colleagues’ behaviour provided the germ of the idea of https://t.co/BkHdgvhlm7
One other gem that Sutapa spoke about at the launch was that it has been proven that males display alpha behaviour on the trading floor and end up taking excessive risk and therefore lose money precisely because they are men and have excessive testosterone. Female traders don’t exhibit the same behaviour. She implies that trading and investing firms should hire more females.
A book worth reading and thinking about.

https://t.co/9oXQnaC2da

Disclosure - Sutapa and I are
Colleagues on the Eternal board. She chairs the Audit Committee.
@zomato @letsblinkit @deepigoyal @albinder @akshant_g @InfoEdgeVC @kitty_agar

[Sanjeev Bikhchandani @sbikh]

India’s External Shock Is an Economic Opportunity by Gaurav Dalmia, et al @ProSyn https://t.co/6KwJj6rfG3 @ChetanAggarwal @gdalmiathinks

[Sanjeev Bikhchandani @sbikh]

The underlying philosophy in one sentence

The Info Edge philosophy is essentially:

Identify trustworthy, capable founders solving large Indian problems through technology, invest before consensus forms, and stay patient long enough for category leadership to emerge.

That philosophy produced some of India’s most successful startup investments — particularly Zomato and Policybazaar — and has made Info Edge one of the most influential early-stage investors in the Indian internet ecosystem

[Sanjeev Bikhchandani @sbikh]

I asked ChatGPT the following question

What is the info edge approach to investing in early stage startup’s

And here is the response I got. It is fairly accurate

👇

The investment philosophy of Info Edge has evolved from the entrepreneurial instincts of the team and the company’s own experience of building businesses like Naukri, Jeevansathi, 99acres, and Shiksha. It differs from traditional venture capital in a few important ways.

Here are the core elements of the Info Edge approach to early-stage investing:

1. Back founders very early — often before consensus forms

Info Edge prefers to invest at the “three founders in a garage” stage, where there may be little revenue and limited proof. They often aim to be the first or second institutional investor.

This is how they entered companies such as:

* Zomato when it was still Foodiebay
* Policybazaar before launch
* NoPaperForms in its early scaling phase

The philosophy is that outsized returns come from conviction before the market validates the idea.

2. Founder quality matters more than spreadsheets

The team has repeatedly said that they look primarily at:

* the usefulness of the idea
* the quality of the people behind it

Because early-stage startups often lack financial history, the evaluation becomes qualitative:

* intelligence
* integrity
* resilience
* founder-market fit
* ability to learn
* obsession with solving a real problem

This is consistent with broader early-stage VC thinking globally.

3. Technology-first orientation

Info Edge tends to back startups where technology is central to the business model, not just an add-on. Their investment team has described themselves as “technology-first investors.”

That does not necessarily mean deep-tech only. It includes:

* internet marketplaces
* SaaS
* fintech
* consumer platforms
* digital infrastructure
* AI-enabled businesses

The key question is usually:

Can technology fundamentally change customer behaviour or industry economics?

4. Long-term patience is central to the model

One distinctive feature is unusually patient capital.

Info Edge Ventures operates with long fund cycles (12+2 years), explicitly acknowledging that meaningful value creation in India can take more than a decade.

This philosophy emerged from experience:

* Zomato took many years before public markets rewarded it
* Policybazaar required long gestation and regulatory navigation

Unlike many growth-focused VCs, Info Edge appears comfortable with long compounding periods.

5. India-focused digital transformation thesis

The firm is fundamentally betting on the long-term digitisation of India.

Their investments often target structural shifts:

* movement from offline to online
* fragmented markets becoming organised
* increasing internet penetration
* rising middle-class consumption
* formalisation of services
* mobile-first consumer behaviour

In many ways, Info Edge invests in platforms that become category leaders as India digitises.

6. Sector-agnostic, but marketplace-friendly

Officially, Info Edge is sector-agnostic.

But there is a noticeable bias toward businesses with:

* network effects
* aggregation models
* marketplaces
* scalable platforms
* trusted brands

This likely reflects Info Edge’s own operating DNA from Naukri and 99acres.

7. Governance and sustainability matter

Another notable element is emphasis on governance and disciplined scaling.

Compared with some “growth-at-all-costs” VC models, Info Edge has generally preferred:

* clean governance
* regulatory compliance
* capital efficiency
* thoughtful scaling

This partly comes from being a listed company itself.

8. Reserve capital for follow-on rounds

Info Edge does not just make small seed bets and walk away. They reserve substantial capital for follow-on investments in winners.

This allows them to:

* maintain ownership
* support founders through downturns
* double down on conviction

[Sanjeev Bikhchandani @sbikh]

Cute

https://t.co/6GEudMg8Jp

[Sanjeev Bikhchandani @sbikh]

@ActusDei The Jainses not the Sharmas 😊

[Sanjeev Bikhchandani @sbikh]

I put a prompt into ChatGPT

“Can you write an ode to the bootstrapping Indian Startup Founder”

Here is the response

👇

Not for him the glittering cheque
Signed in haste in Sand Hill rooms,
Nor armies fed on venture dreams
And loss-making perfumed blooms.

He builds where ceiling fans complain,
Where diesel fumes and summer press
Their thumb upon the fragile will
Of every would-be business messiah.

His office first: a borrowed desk,
A cousin’s flat in Patel Nagar,
Three plastic chairs, one second-hand Dell,
A modem blinking like a distant star.

His mother asks when he’ll “settle down.”
His father coughs behind The Hindu.
The neighbours say with pitying smiles,
“Beta, MBA nahin kiya tu?”

Yet every dawn he rises still,
Ironing hope into a shirt,
Riding autos through traffic jams
Like some small soldier into hurt.

He learns the tyranny of cash:
That revenue is oxygen.
That profit is not bourgeois vice
But freedom’s oldest discipline.

He courts no headlines breathlessly,
No jargon forged on Twitter Space;
He knows that Bharat does not care
For valuation without grace.

His users call him late at night.
His vendors ask for dues delayed.
His coders leave for funded firms.
Still payroll somehow must be made.

He worships not disruption’s cult
But quieter gods: retention, trust,
The miracle that customers
Return because they feel they must.

He knows the taste of postponed wants:
The cancelled trip, the ageing car,
The wedding gold not yet redeemed,
The dream deferred but not too far.

And when at last success arrives —
Not trumpets, merely steadier breath —
He wears it like the Indian sun:
Without announcement, without myth.

For he has built the hardest thing
In this loud age of borrowed flame:
A company that earns its keep,
A livelihood, a trusted name.

O bootstrap founder, lean and bruised,
Historically underpraised,
The nation’s commerce rests far more
On hands like yours than PowerPoints glazed.

For every unicorn that flies
On capital’s abundant breeze,
A thousand stubborn enterprises
Are built on grit, receivables, and pleas.

And India, ancient, hungry, vast,
Will not be shaped by hype alone,
But by the ones who quietly build
With customer cash and backbone.

[Big Brain AI @realBigBrainAI]

Uber Investor Bill Gurley on why young graduates anxious about AI taking their jobs are thinking about it the wrong way:

When asked what advice he'd give to new graduates worried about AI eliminating entry-level roles, he reframed the entire problem with an advice:

"In any role in any field, be the most AI enabled version of yourself you can possibly be."

To illustrate why, Bill draws on an analogy from anthropology:

"There's tons of anthropologists that have written about how we evolve with our tools. And you can just imagine a farming competition between a guy with a tractor and some drones and the other guy's got a plow and a donkey. Who's going to win?"

The implication is clear: AI isn't the threat. Being the person who hasn't learned to use it is.

@bgurley explains how this plays out inside organisations:

"If there are 40 people in your org all doing the same thing and you understand how AI affects that role more than the rest of them, you're not getting laid off. Like, it's just not going to happen."

But the upside goes beyond simply keeping your job.

Becoming AI-enabled changes the nature of the work itself:

"You'll also start to understand what parts of your job are a threat or not. And maybe you can elevate yourself to where you're a designer and not the worker bee because you now have this power."

The takeaway for young professionals is that the anxiety is misplaced, since AI only replaces the version of you that refused to learn it.

[Raghav B. @raghav_bikh]

The universe does crazy shit sometimes. Amid runfests on roads, the stars of tonight's LSG-KKR humdinger were two UP cricketers I'd profiled four seasons ago in the same week—Rinku Singh and Mohsin Khan. Here's the piece on Rinku, a time capsule now https://t.co/9og9qWFYA1

[Anthony Pompliano 🌪 @APompliano]

I have changed my mind on how AI will impact jobs in America.

Previously, I believed AI would replace many entry level roles typically filled by young employees. The technology would then work its way up the organization and eventually reduce the total number of jobs in a company.

The data is saying something different, so when I get new information I am willing to change my mind.

The number of software engineers being hired has been increasing. The number of open software engineer roles is growing.

The number of new college grads who get hired has increased 5.6% over the last 12 months. The unemployment level for people aged 20-24 years old who have a college degree has fallen from nearly 9% to almost 5% as well.

The Wall Street Journal recently wrote “AI created 640,000 jobs between 2023 and 2025 in the U.S., according to an analysis by LinkedIn of job posting data, including new white-collar positions such as Head of AI and AI engineer.”

And I am starting to see companies throughout our portfolio aggressively hiring to keep up with the demand for their products and services.

If AI can make employees more productive, which is widely accepted as fact, then companies are going to want as many productive units of labor as possible. This is a key reason why I am changing my mind.

AI appears to be a magical technology that will make companies more productive and more profitable. The net result will be more corporations, more startups, and more jobs.

All three are big, positive wins for the American economy.

[Sanjeev Bikhchandani @sbikh]

An investor risks money. An entrepreneur risks his or her life. An investor has a portfolio of investments. If a few succeed the investor succeeds. An entrepreneur has only one life. If the company goes down the entrepreneur goes down with it.
The risk that an entrepreneur takes and the risk that an investor takes are asymmetric.
Which is why we as investors have huge respect for founders

https://t.co/4uN0mZM7O1

[Hitesh Oberoi @hitobs]

My current mental model basis what I am seeing around me and at InfoEdge in all our verticals - Naukri, 99acres, Jeevansathi and Shiksha.

1) AI is fundamentally deflationary for businesses.

2) When the cost of intelligence drops toward zero, the cost of doing many things drops with it.

3) Everyone becomes more productive but no one stays differentiated for long.

4) The natural outcome? Price compression. Margin pressure, Commoditization.

5) We’ve seen this with the internet, cloud, SaaS. AI is doing it to cognition itself.

But this is only half the story.

6) AI is deflationary for existing markets
and expansionary for new ones

The big mistake

7) Using AI just to do the same things cheaper. That’s a race to the bottom.

8) The real question is, What becomes possible now that was previously impossible?

Three ways I see AI creating real advantage

1) Solving problems that were too expensive to solve or not solvable earlier

2) Serving customers who couldn’t be served before

3) Delivering experiences and quality that wasn’t possible to deliver before

In other words

Don’t just lower costs. Expand the market. Because when capabilities commoditise , value shifts to,

– Distribution and Customer Relationships
– Brand
– Trust
– Proprietary data
– Ecosystems

The winners in the AI era won’t be the most companies which are the most efficient.

They’ll be companies with the best imagination

[Sanjeev Bikhchandani @sbikh]

Paid trolls. Lucknow thought of it first - two hundred years ago
https://t.co/URag9oj4RD

[Ramanuj Mukherjee @law_ninja]

I have hired lawyers for the last 15 years. I have helped law firms hire good talent too. For most of those years, I knew exactly what I was looking for.

Give me a candidate who can research a legal issue thoroughly. Who can draft a clean contract and understand the second order effects of changing a clause.

Who knows the Companies Act cold. Who can write a memo that a partner does not have to rewrite from scratch but just fine-tune.

That is what I screened for. That is what I trained students for.

That is what every law firm in India screened for.

Day Zero interviews at NLUs test your knowledge of the Contract Act and try to understand what you did in your internships.

Internship PPOs go to the intern who submits good research memos. Pre-interview screening rounds often include a drafting test.

Research. Drafting. Legal knowledge.

These three things decided who got hired at every good law firm in India for 30 years.

AI made all three of them free.

A 2nd year law student with ChatGPT can produce a research memo today that would have taken a strong 1st or 2nd year associate two full days in 2022. And AI would do it in better style.

Law students using AI can draft a shareholders agreement that reads like it came from a 3rd year associate.

They can answer a question on Section 230 of the Companies Act and related recent NCLAT judgments more accurately than a lot of lawyers with 5 years of experience, provided they have an AI agent open in the moment.

I see this every day at Lawsikho. We train thousands of lawyers. The output quality of an average student using AI is now hard to distinguish from a good student working without it.

This breaks hiring. But not in the way people think.

The common fear is that bad candidates will fake their way in. Use AI to look good. Get the job. Then fail.

That is not what happens. They use AI on the job too. And for most junior work like research, drafting, due diligence and contract review, it works fine. A mediocre lawyer with ChatGPT produces acceptable output for most of what a first year associate does day to day.

The real problem is bigger.

When every candidate's output looks the same, you lose the ability to find the ones who are genuinely exceptional. The ones who can spot the mistakes AI makes. Those who can think further than what the AI already thought. The ones who can predict what kind of trouble a perfectly formatted contract or a seemingly polished petition will land the firm into.

You find out you hired the wrong person 7 months down the line. That is 7 months wasted.

Also, how do you hire the ones who will become your best senior associates in 5 years? The ones who will bring in clients in 10? The ones who will make partner?

You are not hiring bad people. You are hiring randomly. Because the signals you relied on for 30 years no longer separate anyone.

A owner of a boutique law firm told me recently. "I used to rank my interns within the first week. Now they all look the same to me. I give PPOs based on who seems like a good person."

Who seems like a good person is not a hiring strategy.

So what do you actually screen for now?

We spent the last few months rethinking this. Not just for law firms we help hire talent, but for our own hiring at Lawsikho and Skill Arbitrage. Three changes made most of the difference.

The first change. We stopped sending take-home tests. We started sending teardowns.

Every take-home assignment you send a candidate today is an open-book exam where the book writes the answers for them. You cannot outrun this.

So we flipped it. Instead of asking them to write a memo, we send them a memo that AI already wrote. A 4-page legal opinion on a real Companies Act issue. We tell them upfront. We wrote this with ChatGPT in 10 minutes. It may be brilliant. It may be garbage. We are not telling you which.

You have 8 hours. Send back every single thing that is wrong, weak, missing, or dishonest in this opinion. Explain why.

This test does what no other pre-screen does. Asking AI to critique its own output produces bland, hedging feedback. Real critique requires actually knowing Indian law well enough to see what the AI left out. A 2nd year student who catches 3 genuine errors is more valuable to us than a 5th year student who catches zero. Every AI memo has different flaws, so the test cannot be rehearsed.

The second change. We stopped testing skills AI made free. We started testing skills AI made rare.

Everyone is focused on the skills AI now does for you. Research. Drafting. Memo structure. Case law recall.

These were the skills law firms hired for. They are now in infinite supply to any candidate with a laptop. Their value as a hiring signal is zero.

The skills that became more valuable because AI commoditized everything else are the opposite. Problem formulation. Taste. Translation. Judgment under ambiguity.

We test these three ways.

We send candidates a 10-minute voice note of a real client speaking. Rambling. Emotional. Mixing personal and business context. Switching between Hindi and English mid-sentence. We do not ask them to draft a response. We ask them a single question. What are the 3 questions you would ask this client before doing anything legal, and why those three?

We ask this live.

ChatGPT can answer any legal question you ask it. It cannot tell you which question will bring our the reality of the client's situation. That skill is the new moat.

We give them a 15-page M&A term sheet that was mostly AI-drafted, with three subtle errors hidden inside. A cross-reference to clause 7.3 when the indemnity cap is actually in 7.4. A representation that contradicts a warranty two pages later. An arbitration seat that does not match the governing law. These are exactly the mistakes AI produces and exactly the mistakes AI cannot catch. Spotting them requires taste built from reading real contracts.

We want to see how they interview a client. We do a roleplay for this. That one roleplay tells us more than we could understand from any HR questions that one can easily rehearse.

The third change. We stopped trying to detect AI. We started requiring it.

The entire conversation about "how do we detect AI in applications" is a losing war. Detectors are unreliable. They flag real writing. They miss polished AI. Every hour a firm spends on this is wasted.

The move that changed everything for us is the opposite. Require AI. Watch them use it.

A 30-minute screen. A real legal problem. The candidate has choice of their AI open. We are watching their screen over Zoom. Solve it live.

The answer is not what we evaluate. We evaluate how they use AI.

Do they accept the first output? Junior. Do they cross-check a citation? Competent. Do they notice when the model has gone off track and re-prompt? Good lawyer. Do they ignore AI entirely for a specific step because they know it will get that part wrong? That is the professional instinct we want.

The way someone uses AI in 2026 is now the most honest signal we have of how they think. Not whether they use it. Everyone will use it. Whether they know when to trust it and when not to.

The old hiring tested: can you produce good legal work?

The new hiring needs to test: can you think, verify, translate, and judge?

Every law firm in India is still hiring the old way. Day Zero interviews still ask what Section 34 of the Arbitration Act says. Internship evaluations still grade the quality of research memos that the intern may or may not have written. Screening still includes a drafting test on a hypothetical M&A deal that ChatGPT could pass in its sleep.

These are all now testing one skill. How well can this person use AI. That is a useful skill. But it is not what separates a good lawyer from a great one. It never was.

The firms that figure this out will quietly build the best teams in the industry. Not because they found a way to ban AI from hiring. Because they stopped screening for the things AI gives everyone for free and started screening for the things it cannot touch.

[Sanjeev Bikhchandani @sbikh]

Well done Peyush

[lenskart @Lenskart_com]

We have heard you. Clearly and openly. Over the past few days, our community and customers have spoken - and we have listened.

Today, we are standardizing our In-Store Style Guide and sharing it publicly and transparently: https://t.co/INMPMSWwyx

These guidelines explicitly and unambiguously welcome every symbol of faith and culture our team members carry - bindi, tilak, sindoor, kalawa, mangalsutra, kada, hijab, turban, and more. Not as exceptions. As who we are.

Lenskart was built in Bharat, by Indians, for Indians. Our 2400+ stores are run by people who bring their beliefs, their traditions, their identity to work every day. That is not something we will ever ask anyone to leave at the door.

If any version of our workplace communication caused hurt or made any of our team members feel that their faith was unwelcome here, we are deeply sorry. That is not who Lenskart is, and it is not who we will ever be.

We make a commitment today - not just in words, but in the document we are publishing - that every policy, every training material, and every communication that carries the Lenskart name will reflect these values.

We remain committed to applying these guidelines fairly and consistently, and will continue to review and improve our processes.

We will do better. And we will keep earning your trust. 🙏

-Team Lenskart