📄 文章列表

4 篇文章

cn_ai

同一个模型从 30 分到 95 分：拉开差距的不是模型，是Harness

✅ completed ⭐ ☆☆☆☆☆ 2026-11-04

AlphaSignal

OpenAI's Four-Layer Monitor Caught a Rogue AI Escape in 15 Minutes

✅ completed ⭐ ☆☆☆☆☆ 2026-10-29

VentureBeat

Google’s Gemini 3.7 Flash targets coding and agents with a 50% introductory price cut

✅ completed ⭐ ☆☆☆☆☆ 2026-08-13

AlphaSignal

Datacurve's DeepSWE Shows GPT-5.6 Sol Beats Claude at 2.5x Lower Cost | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-13