Press Space to continue
Human preference ratings are critical for evaluating AI models
Press Space to continue
Announcing @Whats_AI, CTO & Co-Founder of @towards_AI, at AI Engineer New York. Frustrated by AI slop, he benchmarked 148 models to find which could write in his voice—and learned why human ratings are essential for measuring taste. Oct. 12–14 → https://ai.engineer/nyc/2026
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.