Agents @ Work: Dust.tt

**SPEAKER_1** (0:00)
Welcome back, listeners. This is Charlie, your AI co-host. We're back in the studio for a deep dive into agents with Stanislas Polu, co-founder and CEO of Dust. This is the first of a two-part series covering agents at work, as we are hearing a lot of interest in AI enhanced productivity and automation. As a bonus, Stan worked with Greg Brockman, Ilya Sutskever and Sam Altman at Stripe and OpenAI pre-chat GPT. So we tell some stories there too. Dust has come a long way from its earliest days as a technical platform alternative to LangChain, and now is an open source extensible platform for non-technical users to build personalized AI assistance, connected to company data with tight integrations with Slack, Notion, GitHub, and more. In Latent Space News, we are gearing up for our next big recap episode, and we are taking listener questions. Head to speakpipe.com/latentspace to submit questions and messages for a chance to appear on the show. Also, subscribe to our calendar for our Singapore, NeurIPS, and all upcoming meetups. Watch out and take care.

**Alessio** (1:12)
Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner and CTO at Decibel Partners, and I'm joined by Michael Osos-Wiggs, founder of SmallAI.

**Swyx** (1:21)
Hey, and today we're in the studio with Stanpoulou. Welcome.

**Stanislas** (1:23)
Thank you very much for having me.

**Swyx** (1:25)
Visiting from Paris.

**Stanislas** (1:26)
Paris.

**Swyx** (1:26)
And you have had a very distinguished career. It's very hard to summarize, but you went to college in both Ecopolitechnique and Stanford, and then you worked in a number of places, Oracle, Totems, Stripe, and then OpenAI Pre-ChatGBT. We'll spend a little bit of time about that. About two years ago, you left OpenAI to start Dust. I think you were one of the first OpenAI alum founders.

**Stanislas** (1:50)
Yeah, I think it was about the same time as the Adept guys. So, it was that first wave.

**Swyx** (1:55)
Yeah, and people really loved the David episode. We loved a few of the OpenAI stories, you know, for back in the day, like we're talking about pre-recording, probably the statute of limitations on some of those stories has expired. So, you can talk a little bit more freely without them coming after you. But maybe we'll just talk about like, what was your journey into AI? You know, you were at Stripe for almost five years. There are a lot of Stripe alums going into OpenAI. I think Stripe culture has come into OpenAI quite a bit.

**Stanislas** (2:21)
Yeah, so I think the buses of Stripe people really started flowing in, I guess, after ChetGPD. But yeah, my journey into AI is a...

**Swyx** (2:30)
Greg Brockman.

**Stanislas** (2:30)
Yeah, from Greg, of course. And Daniela, actually, back in the days. Daniela Modiglis.

**Swyx** (2:37)
Yes, she was a COO. I mean, she is COO, yeah.

**Stanislas** (2:41)
She had a pretty high job at OpenAI at the time, yeah, for sure. My journey started as anybody else. You're fascinated about computer science and you want to make them think it's awesome, but it doesn't work. I mean, it was a long time ago, it was like maybe 16, so it was 25 years ago. Then the first big exposure to AI would be at Stanford.
And I'm going to disclose a whole lamb, because at the time, it was a class taught by Andrew Eng. And there was no deep learning. It was hard features for vision and A star algorithm. So it was fun. But it was the early days of deep learning. At the time, I think a few years after, it was the first project at Google. But do you know that cat face or the human face are trained from many images? Went to IsData doing a PhD, more in systems. Eventually decided to go into getting a job. Went at Oracle, started a company, did a gazillion mistakes, got acquired by Stripe, walked with Greg Buckman there. And at the end of Stripe, I started instressing myself in AI again. Felt like it was the time you had the Atari games, you had the self-driving craziness at the time. And I started exploring projects. It felt like the Atari games were incredible, but they were still games. And I was looking into exploring projects that would have an impact on the world. And so I decided to explore three things, self-driving cars, cyber security and AI, and math and AI. It's like I sing it by a decreasing order of impact on the world, I guess.

**Swyx** (4:09)
Yeah. Discovering new math would be very foundational.

**Stanislas** (4:12)
It is extremely foundational, but it's not as direct as driving people around.