fbpx

Michele Catasta

Replit will be at The AI Conference this fall!
VP of AI
Replit

Conference Video

Slides

Michele Catasta – AI Conference

Presentation Title:

What powers Replit Ghostwriter?

Presentation Summary:

Atom icon for The AI Conference 2023, a groundbreaking two-day event on AGI, LLMs, Infrastructure, Alignment, AI Startups, and Neural Architectures.At Replit, our mission is to empower the next billion software creators. Our users build software collaboratively with the power of AI, on any device, without spending a second on setup. We accomplished that by creating from the ground up a delightful developer experience. The Replit development environment allows our users to focus solely on writing software, while most of the hardware (and Cloud computing) complexities are carefully hidden away.

Brain icon for The AI Conference 2023, a groundbreaking two-day event on AGI, LLMs, Infrastructure, Alignment, AI Startups, and Neural Architectures.The focus of this talk will be Ghostwriter, a suite of AI features deeply Integrated in the Replit Development Environment. I will explain in detail how we built a blazing fast Code Completion engine (training a bespoke open-source LLM), how we are constantly evolving our chat-based pair programmer, and (last but not least) how we are creating an Artificial Developer Intelligence (ADI) to make software creation accessible to anyone.

Gradient Flow

album-art

Michele Catasta on AI tools for building software collaboratively.

00:00

About | Michele

Michele Catasta is currently VP of AI at Replit, where he is building the future of software development. In parallel, he is also an AI Advisor at Coatue.

Before that, Michele was Head of Applied Research at X, the moonshot factory (formerly Google X) and, after a successful acquisition, he covered the same position at Google Labs, with a focus on Large Language Models. Michele led a team of AI researchers and engineers, and was also one of the hands-on contributors to PaLM and PaLM-2, Google's most powerful LLMs (and among the 5 most cited AI publications in 2022).

During his academic years, Michele worked at Stanford University as a Research Scientist and Instructor. He graduated at EPFL with a Ph.D. in Computer Science (focused on Applied Machine Learning) and held research positions at MIT Media Lab, Google, and Yahoo Labs.

Lastly, Michele holds the role of Advisor and Early Investor for several AI startups