Karina(@karinanguyen):Great initiative to eval the evals. It incentivizes the industry to build genuinely high-quality benchmarks. Ty for auditing PTB and digging up the old SimpleQA too :)

Karina

@karinanguyen

modelcrafting @thoughtfullab, prev. AI research & product @OpenAI, @AnthropicAI, @maisonagi

가입 February 2019

1.1K 팔로잉 중 44.1K 팬

Karina@karinanguyen

2026.09.18 00:42

Great initiative to eval the evals. It incentivizes the industry to build genuinely high-quality benchmarks. Ty for auditing PTB and digging up the old SimpleQA too :)

Epoch AI@EpochAIResearch

2026.09.17 21:53

Introducing Benchmark Reviews: our new initiative to audit AI benchmarks. We are launching with 15 benchmarks: 4 Verified, 9 Flawed, and 2 with not enough information for a review.