AI 导读
值得一看的出色工作。 超长周期编码任务正是像 Fable 5.1 这样的前沿模型大放异彩的地方。 但这个差距太惊人了(超过约 25 个百分点)。 我觉得有意思的是看看混合智能体的结果,就像 Cursor 所做的那样。
正文
Brilliant effort worth checking out.
Ultra-long horizon coding tasks are where frontier models like Fable 5.1 will shine.
But that's a crazy gap (over ~25 percentage points).
What I think could be interesting is seeing results for a mixture of agents like what Cursor did. https://t.co/bWMJclvtYH
来源:@omarsar0 · x.com