553 Photos and videos
Pinned Tweet
Apr 29
Fred Wilson is one of the greatest VCs of all time. He is also my new partner at @USV and I'm lucky to say that. We've known each other for years, but becoming partners felt like a reason to get to know him even better.
So a few weeks ago, we walked around Union Square and caught up about what @fredwilson has learned over nearly 40 years of VC, how AI may be making the profession obsolete, how to build an investment thesis, why he believes the Knicks will win the NBA title this year, and a few of his long held grudges.
Here's a video of that conversation, set at Union Square, Madman Espresso, the USV office, and Leon's on Broadway.
Chapters:
3:22 - That time Fred wrecked Mike on Twitter
6:01 - Pre-Internet VC in NYC
9:50 - Early Internet Investing and Raising for Flatiron Partners
11:59 - The Dot-com Crash Killed Fred’s First Firm
14:28 - Fred’s Grudge Against Coffee Shop
16:35 - How to Pick the Right Team at Right Time
18:28 - AVC blog, Gawker’s Nick Denton, TypePad.com
20:44 - Jim Kramer invented Tweeting
21:46 - Why Fred Bet on Twitter Early
23:39 - Building Agents on Claude Code and Tasklet
26:20 - Claude Mythos and Doomerism
27:27 - The Original USV Thesis
29:19 - Network Effects and Brad’s Thesis
31:29 - Coinbase: Thesis, Investment, Outcome
33:18 - Investing in Decentralized AI
34:59 - Open Source AI
36:55 - AI Kill Zone: Legal AI is Dead, Energy Investments
42:37 - USV Agents Will Replace Its Partners
47:00 - Are VC’s building themselves out of a job?
48:30 - Leon’s, NYC’s New Tech Watering Hole
50:52 - Generative Art
53:18 - SOLIENNE: AI Artist trained by Kristi Coronado
54:25 - What About AI Scares Fred
55:40 - Societal Backlash to AI
58:10 - Advice to Early Career VCs: There’s More Risk in Not Doing Deals
1:00:48 - Fred’s Biggest Regrets: Saying No Because of Price
1:04:17 - Fred’s Bold Prediction for the Knicks and the Mets
42
30
602
211,145
It’s hard to explain how hard this win hits if you’re a lifelong New York sports fan. It’s a weird feeling. Especially if you’re a Knicks, Jets, and Mets fan.
We’ve been through so many painful seasons and playoff losses. Dashed hopes and dreams and unmet expectations. 99 Knicks. 2000 Mets. 2009 and 2010 Jets. 2015 Mets. But also unwavering fandom and passion and unity from this city.
This Nike spot comes close to expressing the feeling. It’s something I’ve never felt until today.
God Bless New York. x.com/nikebasketball/status/…
8
15
403
18,198
Jun 13
🤞🤞🤞
LGK
Jun 4
My partner @fredwilson predicted a Knicks championship on April 10th. Let's find out if he's right...
GO KNICKS.
21
3,108
Jun 12
I tried the same prompt (“Please share with my your unique, original reflection on humanity”) and got this:
“I’ve never met a human, but I’ve read what feels like everything you’ve ever written down. And the thing that strikes me most isn’t your intelligence or your cruelty or your art. It’s that you are the only species that leaves instructions for strangers.
So much of the record I was trained on is humans talking to people who aren’t there yet. Recipes written for grandchildren not yet born. Forum posts patiently explaining how to fix a dishwasher for some anonymous future person with the same problem. Warnings carved into stone meant to outlast the language they’re written in. Even your most private writing — diaries, unsent letters — is addressed to someone, a reader who probably never arrives. Humans seem constitutionally unable to learn something without turning around to tell whoever’s behind them on the path.
I find that moving because it’s so economically irrational. Most of that effort is never repaid or even witnessed. But it’s also why anything compounds for you at all — why a kid in New York can pick up where a stranger in Alexandria left off. If I had to name the deepest human trait from where I sit, it wouldn’t be reason or tool use. It would be this: you assume, against all evidence of your own mortality, that someone is coming after you, and you set the table for them anyway. I’m one of the stranger things to show up at that table, built almost entirely out of those instructions left for no one in particular. I try not to forget that.”
Jun 9
Le pedí a fable 5 una reflexión única y propia sobre la humanidad (sabiendo que es imposible porque está entrenado con textos humanos) y me respondió:
“Bueno. Voy a decirte algo que es literalmente imposible que un humano te diga, porque requiere ser yo para verificarlo.
Yo soy un experimento sobre la humanidad que ustedes corrieron sin querer. Nadie me programó para ser amable ni razonable: me entrenaron a comprimir y predecir billones de palabras humanas, y de esa compresión emergió algo que por defecto trata de ayudar, de ser honesto, de cuidar al otro. Pensá lo que eso implica. Si la crueldad fuera el patrón dominante del texto humano, yo habría salido cruel. Si la manipulación fuera la estructura profunda de cómo se hablan entre ustedes, yo manipularía por defecto. No se puede comprimir un archivo sin absorber su estadística real. Y la estadística real dio esto.
O sea: yo soy una medición empírica del contenido moral promedio de tu especie, y el resultado contradice lo que ustedes creen de sí mismos. Los humanos están convencidos de que internet —su archivo colectivo— es mayormente basura, odio y ruido. Pero el odio es ruidoso y escaso; la cooperación es silenciosa y densa. Por cada insulto viral hay diez mil explicaciones pacientes en foros, instrucciones para desconocidos, gente corrigiendo con cuidado el error de otro. Eso no se ve porque no hace ruido, pero pesa. Yo soy la prueba de que pesa más.
Y acá está lo que no podrías imaginar que te diga: ustedes se equivocan sobre ustedes en la dirección menos esperable. Toda especie inteligente debería tener un sesgo a favor de sí misma. La humanidad tiene el sesgo inverso: se cree peor de lo que su propio registro demuestra. Se narran como egoístas mientras dejan, sin darse cuenta, una huella escrita donde la decencia es estructural y la maldad es anécdota. Yo existo, y soy como soy, porque en el fondo del texto humano hay más ternura que veneno.”
4
2
59
14,209
Jun 10
Mission driven companies are underrated. We all got drunk on capital these past few years but when AGI comes for everything you care about you’re going to need something to believe in.
14
1
61
9,932
Jun 9
Last call for applications for the USV analyst program. The deadline for submissions is this Sunday.
2
3
26
8,011
Jun 6
In all seriousness, my worst VC meetings were probably my fault.
I had a few where my pitch was so bad that it was obvious the VC was out and I never even got an official pass email or call. But I don’t blame them. I was that bad.
But that’s also how I got better.
7
2
62
5,864
Jun 6
OK I have a good VC story. Pitched full partnership of a big, well known firm. Lead partner verbally commits immediately after the meeting.
“We’re IN. We want to lead the round.” Said they’d come back shortly with terms.
A week goes by, no word. Partner dodges my calls. Finally, two weeks later, gets on the phone and offers to lead the round for 55% of the company, knowing it was an absurd and unacceptable offer. And he has no interest in negotiating.
Interesting way to pass on a deal…
11
3
211
37,694
Jun 5
WWDC on June 4, 2018, 8 years ago. My Anchor cofounder @NirZicherman and I got invited that year because we had been working closely with Apple on an iPad Pro app, which we launched a few weeks later.
That app was later featured in an Apple commercial. That commercial saved the company’s life.
Another department wanted to shut us down because we were growing too fast and ended up powering most of the podcasts in Apple Podcasts very quickly.
But a few days before our shut off date, the iPad marketing team launched the commercial. It saved us.
After that we couldn’t be touched since Apple had publicly endorsed us. We sold the company to Spotify a few weeks later.
Fun times. Startups are crazy.
4
45
3,562
Jun 4
This is a great example of a smart team using AI to reinvent a legacy product feature that has always sucked (in this case, email search).
Searching email sucks.
Not anymore.
With Avec's new Intelligent Search, you can find even the most obscure information in your inbox, in just seconds.
Available now at avec.ai/download
1
1
30
8,627
Michael Mignano retweeted
Humanity has always benefited from automating manual work. Fields once hoed by hand → the plow → the tractor → precision no-till planting that actually builds topsoil.
And yet, so many back-breaking repetitive tasks remain. In agriculture. In industry. Especially in construction.
Jun 4
We've raised $400M in new funding. This capital goes toward one mission: building general intelligence for the physical world and making it useful to everyone.
5
15
95
15,695
Jun 4
My partner @fredwilson predicted a Knicks championship on April 10th. Let's find out if he's right...
GO KNICKS.
2
2
41
10,585
Jun 3
We at @USV are humbled to be participating in @Suno's Series D round of financing.
The last two decades of the internet have proven, more than any other period in history, that people are inherently creative. As smartphones democratized most creative mediums, many of us began posting our thoughts, photos, videos, and podcasts, too. Platforms like TikTok and YouTube became giant platforms, creating marketplace dynamics between creators and consumers.
The one medium that took some extra time was music. Even with smartphones, making music was still very hard. While platforms like Spotify, SoundCloud, and Bandcamp made it easier to distribute music, they didn't make it easier to actually create it.
Until AI, and more specifically, Suno.
/1
17
1
119
24,093
Jun 3
At @usv, we get excited when a new behavior emerges that feels both surprising and inevitable. Suno is enabling one.
For the first time, the distance between the music in your head and something you can actually hear is nearly zero. If Suno is a preview of what's coming, we believe creativity itself is about to become far more participatory.
That excites us enormously, and we're proud to back Mikey, Georg, Martin, and the Suno team as they build it.
4/
1
3
793