Irene Solaiman, Hugging Face's chief policy officer, said the push to place third-party evaluators inside AI labs won't fix the industry's oversight problems on its own, because the evaluations those observers rely on are still an immature science. She spoke on Thursday, Oct. 15, in a TechCrunch Disrupt session titled "Before You Let AI Do the Job, How Do You Know It Actually Can," and TechCrunch reported her remarks on Oct. 19.

Asked whether current tests can be trusted, Solaiman tied trust to reproducibility and access. "Trust is such a weighted term," she said. "In terms of whether we can trust results, one big part [of that] is can you reproduce the results of an evaluation? Do you have the level of access that you need to the model itself — this is where open weights come in in a big way."

She also said there is no good way yet to compare one evaluation with another. "They are an evolving science — where we don't know how to meaningfully compare them to each other," Solaiman said.…