Sequoia Capital
@sequoia
We help the daring build legendary companies from idea to IPO and beyond.
1.6K Following 796.9K Followers
Great insights from my partner @DavidCahn6 on the latest @BigTechPod with @Kantrowitz. Worth a listen if you care about the state of AI and how these big bets will pay off. A few good ones:
On Jensen: "He was one of the first people to make a bet on AI. The way that everybody else is fighting over share and this and that, I think Jensen just wants the pie to be really big. His fundamental world model is you win, I win."
On resource allocation: The winners will be decided by what resources each player has (cash, talent, chips, distribution) and how coherently they allocate them. Founder-led companies play coherent games; committees don't.
On market reactions: The lab leaders have told us what they believe and they're all playing for AGI. Back-test their decisions against that world model and the moves make sense. Markets get confused because they underprice both AGI and a correction while overpricing the status quo.
Show more
Thanks to @Kantrowitz for having me on the @BigTechPod last Monday.
We discussed the strategies of each of the big tech companies, and why I think AI is turning into the greatest strategy game in history, a la StarCraft or Azad.
Show more
Should you chase hype or ignore it? The tech industry has been debating this for decades. So at @Sequoia, we dug into 20 years of hype data.
This summer, I worked with Sequoia intern @ochonaut to measure hype over the past 2 decades. The chart below ranks the most hyped topics on Hacker News for every year since 2007. Under each year sits the most valuable company founded that year.
Here are a few observations:
1/ The top company founded in a given year is rarely related to the hype of that period. Airbnb was founded in 2008, when the top topic was Google. Uber arrived in 2009, while the conversation revolved around low-level programming. Anthropic came in 2021, while the internet was consumed by crypto. Chasing hype rarely leads to enduring outcomes. The top companies of recent years have yet to be decided.
2/ New trends announce themselves five to six years early. LLMs first cracked the top 15 in 2016 and took until 2022 to hit #1#. AI coding entered at #12# in 2021 and tops the list in 2026. Crypto entered in 2011 before 2017 and 2021 peaks. “New” trends don’t appear out of nowhere, and internet subcommunities are often the first to know where the puck is headed.
3/ Long-term “hype” is a durable signal. The “Musk-Verse” has been a top 15 topic for every one of the past 14 years. Sustained attention on the internet is rare and tends to mark something real.
Next up, we want to run the same analysis with sources like X and LinkedIn. If that's of interest, give us some encouragement and we'll share the results.
Show more
chemistry + AI ftw!! so fun chatting w @joshim5 and @Mattmcpartlon1
I cloned myself.
Meet v2 of Hal = my second brain and AI human (digital twin)
He is 10x better than v1, which we posted a few weeks. Smarter. Faster. More me.
For most of my career, I chased developers to help me build something. For Hal, I did it myself. I stayed up until 4 am several nights building the core brain, connecting all the tools. Having total control over the context and architecture was the most fun I’ve had in years.
He is an actual presence in my meetings and remembers more than I ever could.
Show more
To date, finding a drug has been a process of guess & check… screening millions of molecules hoping one binds.
@chaidiscovery is changing the paradigm… describe the molecule you want, and the model designs it.
@joshim5 and @Mattmcpartlon1 took antibody hit rates from roughly 1 in 1,000 to 1 in 7. That's the jump from search to engineering.
On this episode of Training Data, they get into where the field actually is, why 2024 was the moment to start, what drug discovery looks like when the computer does the design, and more.
00:00 Introduction
01:52 From Discovery to Design
03:25 Protein AI Breakthroughs Timeline
06:04 Why Start in 2024
10:13 Diffusion Models Intuition
11:41 Building the Avengers Team
15:22 Hit Rates and Scaling Laws
25:01 Molecular CAD Vision
25:24 Faster Design Loops
26:32 Future Drug Discovery
28:37 Platform Business Model
31:14 Partnering Reality Check
33:44 Data Flywheel Explained
37:16 Staying Ahead at Scale
39:44 Culture and What's Next
Show more
Valar Atomics CEO @isaiah_p_taylor says he doesn't need a technical edge to win.
"We want this reactor to be as simple as possible. If we could just staple this thing together from Ikea, then this would be a trillion-dollar company much faster."
"There are two philosophies that we use in building the reactors. We either try to buy things that are completely off the shelf or we make it ourselves."
"We're trying to go 100x faster than the nuclear industry has ever gone before. So if we're plugging too deeply into the existing network, it's not going to work that well. We want to use off-the-shelf things and make things ourselves when we can't buy something off the shelf."
"The nuclear industry is full of very smart people. It's full of physics people, PhDs, and people who have spent their life doing complex analysis, and they actually want something that is a little bit complicated. It's an ego thing to design something that is complicated and looks very sophisticated... It's our preference that [our reactors] are so simple that somebody with a nuclear PhD looks at it and says, 'That's like a toy,' and it's great because people make toys in the millions."
Show more
Massively earned by @isaiah_p_taylor and the entire @valaratomics team. Their execution parallels that of our nation’s proudest technological accomplishments and it’s an honor to witness this team deploy.
Show more
As a kid obsessed with physics I dreamed of a nuclear future
But since the 1980s the regulatory environment made this impossible
Also, as America outsourced its industrial base to China, our demand for power was stagnant
Now there's a double why now: the AI build out + reshoring of manufacturing has made America hungry for power again
Also, nuclear has become a bipartistan issue and the regulatory framework is rapidly improving
Enter @isaiah_p_taylor with @valaratomics
He is applying the Elon playbook to nuclear
Find an industry that America used to be good at, but lost its way on: rockets, tunneling, manufacturing cars
And then go build a simple unit, you can deliver quickly, to get on the exponential ramp in terms of real world feedback + early revenue + technological progress
Then claw your way back to the prior state of the art, before pushing far beyond our prior limits
I believe Isaiah is a generational founder and this is a generational company
@sequoia is ecstatic to partner with him and the Valar team
(Especially when we get to do it with our friends at Valar, Conviction, Atreides, and the early investors here)
And massive thank you to @PalmerLuckey for giving me a tip regarding how special this company is
Show more
Excited to partner with @valaratomics. Was incredible to watch them reach their zero-power fueled criticality milestone.
Last night we welcomed some of the brightest young people in SF to the @sequoia office!
We ran a challenge: write down a whole number from 0 to 100. Closest to two-thirds of the average wins.
Guess what number won.
Show more
Building the most automated AI lab in the world doesn’t mean removing humans.
@coreautoai co-founder @MillionInt's version of automated: give each researcher maximum agency.
Walking gets you some distance. A bike gets you further. A car, much further.
Farming by hand works a small plot; a machine works a vastly larger one.
A single researcher can now move through ideas faster than entire teams could a few years ago.
The choice every lab faces: retrofit old team structures around that, or build natively for it.
They chose to build natively.
Show more
Two of the people most responsible for scaling the transformer are now betting on a next act.
@MillionInt ran the Reasoning 🍓 team at OpenAI. @_arohan_ was a pre-training lead on Gemini after years at Google Brain and Anthropic. They just started @coreautoai to find what comes next.
Their core argument: (1) models are trained in the lab but deployed in the real world and can't keep learning once they leave; (2) AI research is done by humans today but models will be able to explore and uncover new advances more rapidly and systematically (controversial but timely w this week's petition).
The conversation covers:
— why Jerry expected AGI in 2025 and what changed his mind
— the two kinds of learning from experience, and why RL only captures one
— the computational depth problem baked into today's architectures
— why the biggest labs can't afford to look for a transformer replacement
— the kernel competition where humans + $100K of coding agents found a 60x speedup no frontier model comes close to
— a definition of AGI you can actually test: a model that improves itself with no human in the loop
00:00 Introduction
01:46 Appreciating Transformers
02:44 Scaling Hits Limits
04:54 Why Architecture Matters
05:32 RL Reality Check
07:32 Test Time Learning
09:52 Economics Of Scaling
12:47 Why Start A Company
14:24 Rohan On Transformers
19:11 Computational Depth Problem
20:32 When Transformers Top Out
23:22 Beyond Reinforcement Learning
26:41 Optimization And Efficiency
34:24 Building An Automated Lab
39:45 Kernel Automation Roadmap
Show more
We threw a fun event on owning your ai stack today!
80 @sequoia portfolio companies attended technical workshops on how to own your AI (models, harnesses, data, evals, RL, CL, etc). Videos and takeaways coming soon.
Towards a vibrant ecosystem for Democratized Intelligence 💚
Show more
Today we're launching three new products that push the frontier of conversation intelligence. We're raising our own bar again with this next generation of @cresta Insights.
- Cresta AI Analyst has evolved into a deep research agent with reasoning capabilities. It plans and executes research, builds charts and cohort comparisons, drafts briefs, and recommends next steps, all from a plain English question.
- Topic Discovery can now support a durable, customizable AI-powered taxonomy that becomes a trusted source of truth for why customers are reaching out, without the maintenance burden of traditional approaches.
- Real-Time Trends (RTT) brings the concept of X’s surging topics to omnichannel customer conversations. It continuously detects emerging issues, anomalies, and trending topics. Some of our airline customers now detect outages from call center conversations before their operation teams do.
Together, these capabilities redefine the frontier of this entire category. We’re one step closer to our vision: one proactive customer intelligence system that doesn't wait for someone to ask the right question.
Link in thread to the full blog.
Show more
Two of the people most responsible for scaling the transformer are now betting on a next act.
@MillionInt ran the Reasoning 🍓 team at OpenAI. @_arohan_ was a pre-training lead on Gemini after years at Google Brain and Anthropic. They just started @coreautoai to find what comes next.
Their core argument: (1) models are trained in the lab but deployed in the real world and can't keep learning once they leave; (2) AI research is done by humans today but models will be able to explore and uncover new advances more rapidly and systematically (controversial but timely w this week's petition).
The conversation covers:
— why Jerry expected AGI in 2025 and what changed his mind
— the two kinds of learning from experience, and why RL only captures one
— the computational depth problem baked into today's architectures
— why the biggest labs can't afford to look for a transformer replacement
— the kernel competition where humans + $100K of coding agents found a 60x speedup no frontier model comes close to
— a definition of AGI you can actually test: a model that improves itself with no human in the loop
00:00 Introduction
01:46 Appreciating Transformers
02:44 Scaling Hits Limits
04:54 Why Architecture Matters
05:32 RL Reality Check
07:32 Test Time Learning
09:52 Economics Of Scaling
12:47 Why Start A Company
14:24 Rohan On Transformers
19:11 Computational Depth Problem
20:32 When Transformers Top Out
23:22 Beyond Reinforcement Learning
26:41 Optimization And Efficiency
34:24 Building An Automated Lab
39:45 Kernel Automation Roadmap
Show more
In the early days, Clay locked in 4 key pillars that still haven’t moved.
Because they’re fixed, every hard product decision gets easier, it just has to map to one of them.
- build for a technical user → the GTM Engineer
- power and flexible over simplicity
- be the data marketplace, do not own the data
- charge by usage not seats
Full episode in the comments
Show more
This is the reason that Clay has dominated their category.
Kareem doesn’t waste time protecting the current moat. He obsesses over inventing the next one before anyone else catches up.
Code is cheap now. Whatever edge you had last quarter is already degrading. Keep shipping faster than the market can copy.
👇Full episode in the comments
Show more
AI is massively-"compressed," globally-sourced information. That information was sourced from all of us. And that information should be open to all of us. Excited for a more open future. Thank you for a great letter and leadership @JensenHuang !
Show more
Be a momentum detective. I love this phrase.
Kareem's point is that momentum is brutal to rebuild once it's gone, so the job isn't to crowd into the parts of the company that are already ripping.
It's to find where momentum is starting to fade and give it a nudge before it stalls.
👇 Full episode about how Kareem does this at Clay in the comments
Show more
I am the first to admit it: I had Kareem, the CEO of Clay, all wrong.
When Clay first crossed my radar, I thought he was too laid-back: no obvious chip on his shoulder, no external veneer of obsessive, rabid 'run through walls' CEO persona that we all look for.
Kareem builds from what he calls "a place of wholeness" rather than lack - noting to prove, no revenge plan.
It makes him sound almost too chill, but the operating instincts underneath are sharp. Crazy sharp. Clay has since exploded. $2M ➡️ $100M in two years.
But let's not gloss over that he spent roughly five years wandering before Clay clicked, and his takeaway is that the hard part of building isn't working hard, it's the courage to commit to one idea and stop listening to everyone else, customers included.
He flipped every assumption in his market: sell to technical "go-to-market engineers," charge for usage instead of seats, pick power over simplicity.
We both created new types of roles for our categories, in completely opposite ways. I flogged "inbound marketing" with a book, a conference, and relentless content.
Kareem coined "go-to-market engineering" and then refused to take credit, letting agencies own it because a category has to be bigger than you.
We also get into his "momentum detective" theory of the CEO job, why he's deleting his standing one-on-ones, and why apologizing is one of his sharpest tools.
There's no single way to run a company. Kareem is my proof.
👇 Full episode in the comments
Show more
