PulseAugur
中
实时 20:16:02
English(EN) Researchers tested five frontier artificial intelligence models with 1,000 real-world fact-checking prompts. The systems failed to reach a consensus on 67 perce

研究人员使用 1000 个真实世界的事实核查提示测试了五个前沿人工智能模型。这些系统在 67% 的问题上未能达成共识。

作者 PulseAugur 编辑部 · [1 个来源] ·

在 Mastodon — fosstodon.org 阅读 →

报道来源 [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Researchers tested five frontier artificial intelligence models with 1,000 real-world fact-checking prompts. The systems failed to reach a consensus on 67 perce

    Researchers tested five frontier artificial intelligence models with 1,000 real-world fact-checking prompts. The systems failed to reach a consensus on 67 percent of the queries, actively disagreeing with each other on the basic facts. # AI # TechNews # MachineLearning # Cyber ht…