A New Age in Evaluation of e-Commerce Search: The LLM Judge
Every search team we've spoken to reports the same pattern: offline metric improves, model ships, revenue doesn't move. Is the "LLM Judge" the answer?
A blend of the finest ingredients to always hit the spot.
From machine learning researchers to engineers, we're all fermenting ideas into reality—one dill-icious innovation at a time.
Two timezones, one kitchen. London ships product, Cape Town ships papers.
Open-notebook research. Methods, confidence intervals, and the experiments that didn't work.