Reality: The Final Eval — Lukas Petersson and Axel Backlund of Andon Labs

Thank you for having us. Yeah, I'm Lucas and I'm Axel.

It goes beyond the title with direct discussion of like, yeah, think, including: Thank you for having us.

1. 01Yeah, so we did work with, like, Anthropic was one of our early customers in doing evals
2. 02So we did, like, dangerous capability evals, nothing we published openly
3. 03But then we started thinking about doing some kind of public benchmark