Technology
Embedded AI evaluators won’t be an easy solution, Hugging Face’s policy chief says
Source: TechCrunch · Published
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 […]
Related stories
- New AI tool can predict cancer survival by a single patient selfie, study suggests
The Guardian · 19 Oct 2026, 22:30
- Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’
TechCrunch · 19 Oct 2026, 22:04
- Amazon is taking its biggest shot at Nvidia yet with new TorchNeuron dev tool
TechCrunch · 19 Oct 2026, 20:09
- Hackers hit AI coding tool OpenCode, running up charges on users’ AI accounts
TechCrunch · 19 Oct 2026, 19:28
- Tolan snags $30M for its AI companion that helps users navigate life
TechCrunch · 19 Oct 2026, 19:00
- Replika’s founder built the AI assistant she pitched at Disrupt 12 years ago
TechCrunch · 19 Oct 2026, 18:49
We are a news aggregator: we show the headline and a short excerpt with a link to the original source. We never republish full articles.