Traverse Launches: Data Research for the Non-Verifiable

Traverse recently launched!

‍

^{"Traverse the path to super intelligence"}

‍

^{TL;DR: Traverse is a data research lab focused on the hardest unsolved problem in frontier model training: ambiguous, taste-dependent work. We capture real human behavior in highly controlled settings and turn judgment, taste, and long-horizon reasoning into high-fidelity environments for frontier models.}

‍

https://youtu.be/CsDg8PYfg64

‍

Founded by Lance Yan & Zachary Yu

‍

The Problem

Reinforcement learning has already helped frontier models achieve superhuman ability in math and coding since these domains have very clean and deterministic feedback loops.

However, the next frontier domains (law, healthcare, sales, writing, etc) aren’t as black and white. Current approaches fail to accurately represent subjective scenarios, despite these domains being where most of the economic value is.

‍

The Solution

The team is building data factories to create high fidelity real life work environments at scale.

Traverse captures what people actually think while doing their work; they are pioneering a new category of training data that is yet to exist.

Learn More

‍

^{Visit www.traverse.so to learn more.}

‍

^{If you’d like to understand the details, reach out to the founders here.}

‍

^{Follow Traverse on LinkedIn & X.}

‍

‍