跳到正文
elvis· @omarsar0 · X·· 3 小时前AI 评分42
AI 导读

和 Jev 一样,我相信 RL 会解锁更多类似这样的成果,大幅削减关键智能体操作的成本。 flow-1 在性能上很有竞争力,但在发现智能体追踪中的故障方面能大幅节省成本。 RSI 不只适用于通用智能。它同样会加速专用智能。

正文

Like Jev, I believe RL will unlock several more like this, slashing the cost of critical agent operations.

flow-1 is competitive in performance, but a huge cost-saver for finding failures in agent traces.

RSI doesn't only apply to general intelligence. It will equally accelerate specialized intelligence.

引用Robert@skull8888888888
Introducing flow-1, our new model trained with RL to find errors in agent traces. It matches GPT-6-sol in trace intelligence while being 23x cheaper. It also costs 25% less to run than GPT-6-luna. flow-1 finally makes it possible to monitor and understand every agent run, without sampling. 1/6
在 X 查看被引用的帖子

来源:elvis · x.com