Kiln pointed a coding-agent research loop at Jev, a closed-set classifier from TypeSafe that returns one of the options you give it, with probabilities, and no text. The task was choosing the right pinyin reading for polyphonic Chinese…
In the News: October 19, 2026 (Evening)
Kiln says an autoresearch loop that rewrote the code around a classifier cut its errors on one task to 147, against 285 for a reasoning model.
Evening edition
Machine-readable
Download Markdown