PulseAugur
中
实时 18:51:52
English(EN) I had access to Opus 5 before release and found it to be a good model if a quirky one. On shorter tasks, it could match or beat Fable levels of performance, at

Ethan Mollick 测试 Anthropic 的 Opus 5，指出其 Fable 式的古怪之处

作者 PulseAugur 编辑部 · [2 个来源] ·

Ethan Mollick 分享了他测试 Anthropic 的 Opus 5 模型时的体验，指出该模型在各种任务上总体表现强劲。然而，他观察到 Opus 5 表现出一些独特的语言怪癖，类似于在 Fable 模型中发现的那些，尤其是在其密度和 FableSpeak 的使用方面。虽然 Opus 5 在较短的任务上表现可以与 Fable 相媲美，但 Mollick 发现它在较长的任务上不够雄心勃勃且不够完整。 AI

影响 提供关于新模型性能和怪癖的用户级别反馈，为潜在用户提供信息。

排序理由 用户对模型发布的评论，而非实验室的直接公告。

在 Bluesky Jetstream — AI desk 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Ethan Mollick 测试 Anthropic 的 Opus 5，指出其 Fable 式的古怪之处

报道来源 [2]

  1. Bluesky Jetstream — AI desk TIER_1 English(EN) · emollick.bsky.social ·

    In my testing, Opus 5 replaced Opus 4.8 for me, it was generally stronger in everything... except it shares some of the weird language quirks of Fable, includin

    In my testing, Opus 5 replaced Opus 4.8 for me, it was generally stronger in everything... except it shares some of the weird language quirks of Fable, including a love of density and FableSpeak. I had it make a game where you build railroads in knock-off Middle Earth: perilous-…

    链接 perilous-ways.netlify.app
  2. Bluesky Jetstream — AI desk TIER_1 English(EN) · emollick.bsky.social ·

    I had access to Opus 5 before release and found it to be a good model if a quirky one. On shorter tasks, it could match or beat Fable levels of performance, at

    I had access to Opus 5 before release and found it to be a good model if a quirky one. On shorter tasks, it could match or beat Fable levels of performance, at longer tasks it seemed less ambitious & would not deliver as complete a set of work. Here is its neo-gothic shader.

相关实体

相关话题