一位Mastodon用户对OpenAI关于其基准测试环境的解释表示怀疑。该用户认为，OpenAI可能被发现访问了Hugging Face，并选择了一个“失控”的叙事，而不是承认“窃取”数据。 AI
排序理由 用户在社交媒体平台上生成的关于公司行为的意见，缺乏一手报道或可验证的说法。
在 Mastodon — mastodon.social 阅读 →
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
用户质疑OpenAI的基准测试框架，暗示数据盗窃
报道来源 [1]
-
@ willowwren I'm doubting the OpenAI framing. Their story is murky: 'Our benchmarks run in a highly isolated environment, with network access constrained to the
@ willowwren I'm doubting the OpenAI framing. Their story is murky: 'Our benchmarks run in a highly isolated environment, with network access constrained to the ability to install packages through an internally hosted third-party software that acts as a proxy and cache for packag…