alt Hacker NewsThis is why using other LLMs as scorers for benchmarks and evaluations is such a bad idea, they'll have preferences you can't anticipate and won't understand immediately.
This is why using other LLMs as scorers for benchmarks and evaluations is such a bad idea, they'll have preferences you can't anticipate and won't understand immediately.
The idea that that LLM reliability or bias can be solved with more LLM is... infuriatingly persistent.