Embedded AI evaluators won’t be an easy solution, Hugging Face’s policy chief says
AI labs have staked their reputations on model benchmarking — the supposedly neutral and accurate system of evaluations that are designed to measure whether one AI product is better than another. However, the methods behind these evaluations are complicated and still maturing, said Irene Solaiman, H
Buy One Founder Summit Ticket, Get a Second for Free. Register now.
Disrupt doors open Oct. 13. Get your pass and bring someone with you at 50% off. REGISTER NOW.
TechCrunch Desktop Logo TechCrunch Mobile Logo Latest Startups Venture Apple Security AI Apps Disrupt 2026 Events Podcasts Newsletters Search Submit Site Search Toggle Mega Menu Toggle Topics Latest
Embedded AI evaluators won’t be an easy solution, Hugging Face’s policy chief says Lucas Ropek 3:49 PM PDT · October 19, 2026 AI labs have staked their reputations on model benchmarking — the supposedly neutral and accurate system of evaluations that are designed to measure whether one AI product is better than another.
However, the methods behind these evaluations are complicated and still maturing, said Irene Solaiman, Hugging Face’s chief policy officer, during a discussion at TechCrunch Disrupt last week. Testing needs to come together into a more consistent science if the industry is to rely on them in the future.
With that in mind, can we trust the current tests that are being released?
“Trust is such a weighted term,” said Solaiman. “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 added.
Reproducibility in model evaluations has long remained one of the stickier aspects of benchmarking — and remains a topic of significant debate in the industry.
Outside of an individual test’s validity, there’s also the added question of how that test compares to other evaluations.
“They are an evolving science — where we don’t know how to meaningfully compare them to each other,” Solaiman said.
“They start to get ineffective relatively quickly, and we don’t have as much of a thriving ecosystem as we need,” she added. “There’s this hunger for an embedded evaluator ecosystem now, but the qualifications that determine who is an effective evaluator across what tasks need a lot more standardization.”
The idea of embedded evaluators — in which supposedly “neutral” third-party observers are placed inside AI organizations — has been popularized over the last several months, as AI labs grapple with a rash of safety incidents that have spurred concerns over the potential harms of their technology. Hugging Face was famously the target of one of those incidents.
Instead of active government regulation to identify and mitigate model safety concerns, labs have pushed for the third-party solution. However, doubts remain over how neutral or effective those evaluators will actually be. Anthropic’s decision to hire Accenture as its first evaluator spurred a good amount of backlash, with some critics mocking the idea that the consulting firm was qualified to do the task at hand.
Evaluations are now moving from merely a test of the model itself to a test of the entire system around the model — including the harness and agent. The harness — or the tool the user is using to access the model — specifically, has a lot to do with a model’s performance, and a weaker model with a better harness could easily out perform a frontier model, Soleiman shared.
“Agentic evals are really hard and really expensive,” said Solaiman. “We have just more evaluations for models. … We don’t have as many evaluations for harnesses, and we are developing better evaluations for the holistic agent — because that’s what a lot of folks are getting value out of,” she added.
In other words: the evaluation space is a bit of a free-for-all at the moment, and if benchmarking is going to continue to be seen as a useful tool for industry leaders, a more uniform, industry-wide approach — where everyone is on the same page — may be necessary.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.
November 4 Boston Buy One Pass, Get a Second Free Cover more ground at TechCrunch’s ultimate founder bootcamp of the year by bringing your co-founder or partner for free Book before the BOGO deal expires
Anthropic says its workforce has become less junior and is spending more time in meetings Anthony Ha
Replit makes OpenAI its default over Anthropic, CEO says Kirsten Korosec Lucas Ropek Rebecca Bellan
Mark Wahlberg wants to take on the longevity-startup crowd with an affordable gym concept Connie Loizos
Tesla reveals SpaceX-powered Roadster that flies and falls with style Sean O'Kane
FBI arrests OpenAI employee accused of planting hidden recording device in conference room Zack Whittaker
Bumble agrees to a $1.3B acquisition deal as online dating faces a reset Lauren Forristal
Just 5 years in, interactive chatbot platform Character.AI files for bankruptcy Ivan Mehta
X LinkedIn Facebook Instagram youTube Mastodon Threads Bluesky TechCrunch Staff Contact Us Advertise Site Map Terms of Service Privacy Policy RSS Terms of Use Code of Conduct Voice AI Anthropic Flock Startup Battlefield Disrupt 2026 Tech Layoffs ChatGPT © 2026 TechCrunch Media LLC.