← Front page

Training Data · Tuesday, August 4, 2026

Chai Discovery Achieves 15% Antibody Binding Success Rate with AI

Chai Discovery has significantly improved the success rate of AI-driven antibody design, increasing it from 0.1% to 15% with their Chai 2 model. This leap in accuracy allows for more robust data collection and analysis of molecular properties. The company focuses on end-to-end generative design, taking an idea from concept to a testable molecule in the lab, differentiating them from competitors who may only assist in finding existing molecules.

companyChai Discovery

The tape

3 quotes
So we really focused in on how do we just make this process more accurate. We got to, uh, with our Chai 2 model about a 15% success rate.
Matt
So now if you screen out a thousand molecules, you're getting 150 back. And then you can start to get some like interesting statistics on the properties of the molecules.
Matt
So, you know, we're not just, uh, you know, building a tool that helps you find good molecules. We're actually building a platform that allows you to go from idea to actual molecule in the lab, uh, that can be tested.
Matt
Heard on Training Data — “Chai Discovery's Bitter Lesson: Drug Design Is Another Scaling Problem, published Tuesday, August 4, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.03