Image created with gemini-3.1-flash-image-preview with claude-opus-4.7. Image prompt: A Lutheran stained-glass panel of a majestic white crane in mid-flight carrying a glowing scroll of Chinese characters in its beak, gazing up at a red-tailed hawk with a cat in its talons soaring above, set against a hybrid gothic-pagoda cathedral silhouette amid leafy Virginia hardwoods, jewel-tone cobalt sapphire ruby amber and emerald glass with bold black leading, radiant backlit halos, gold-leaf accents, and a heavy blackletter title-card banner at the base reading ‘ZHIPU AI’.
📖 The second half of LLM evaluation has officially begun. A fantastic deep dive from Zhihu contributor 李磊NLP on why the Agent era is forcing us to rethink almost everything about AI evals. 2026 may ultimately be remembered as the year Agents moved from demos → production.
https://x.com/ZhihuFrontier/status/2056408194801635391
Leave a Reply