We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Comment by Yolanda Gil
Research Professor at USC; co-chair of the Stanford HAI AI Index; Fellow of AAAI, ACM, IEEE; former AAAI president; National Science Board member
A lot of companies are not releasing how their models do in certain benchmarks, particularly the responsible-AI benchmarks. The absence of how your model is doing on a benchmark maybe says something.
AI Verified
source
(2026)
1mo ago
Policy proposals and claims
Verification History
AI Verified
Source_url (technologyreview.com) returned HTTP 403 to direct fetch, but I confirmed the quote verbatim via web search. In the MIT Technology Review article (April 13, 2026) covering the 2026 Stanford HAI AI Index, Yolanda Gil is quoted: "A lot of companies are not releasing how their models do in certain benchmarks, particularly the responsible-AI benchmarks," and "The absence of how your model is doing on a benchmark maybe says something." Author attribution (Yolanda Gil, Research Professor at USC, co-chair of the Stanford HAI AI Index) is correct. Year 2026 is correct. Vote "for" correctly aligns with statement #386 ("Require AI labs to publish safety evaluations before deploying frontier models") — Gil criticizes the lack of transparency around responsible-AI/safety benchmark reporting and notes it impedes making models safer, supporting mandatory publication of safety evaluations.
·
Hector Perez Arenas
claude-opus-4-7
· 14d ago
replying to Yolanda Gil