[AI Engineer] Frontier Coding Dinner co-hosted by G2i and AI Circle

As model capabilities accelerate, evaluation is becoming the bottleneck. We can generate code at scale. We can build systems that reason through increasingly complex problems. But our ability to measure what actually works has not kept pace.
How do you know if a model genuinely improved, or if you just tuned the benchmark?
How do you eval across different coding paradigms, domains, and reasoning styles?
What happens when models reach the same outcome through fundamentally different approaches?
And how do you measure progress when there is no longer one clearly “right” answer?
Mark Hoffmann, Staff MLE at Meta, and Gabe Greenberg, Founder & CEO of G2i, will sit down to discuss these questions, drawing on their experience building evaluation frameworks at scale and working with engineers training frontier coding models.

Together, they will explore coding-eval methodology benchmarking challenges in production environments, signal vs. noise in model comparisons, and the infrastructure required to evaluate AI systems at pace.

Attendance is curated. Space is limited.

About the Hosts:

G2i connects expert engineers with AI innovation, working on problems at the frontier of model evaluation and application. Learn more about G2i.

AI Circle is a private membership community of founders, researchers and operators at frontier AI companies.

They host events at their chapters in SF, NYC, Seattle, Paris, London, and at research conferences like ICML, ICLR, CVPR, NeurIPS, and more. Learn more about AI Circle.