elvis· @omarsar0 · X·· 3 小时前AI 评分63
AI 导读
flow-1 是一个用 RL 训练的新模型，用于在智能体轨迹中找出错误，其轨迹智能水平与 GPT-6-sol 相当，但成本低 23 倍，运行成本也比 GPT-6-luna 低 25%。该模型让无需采样的全量智能体运行监控成为可能。Elvis Saravia 转发并评论称，RL 会解锁更多此类模型，大幅降低关键智能体操作的成本，RSI 同样会加速专用智能的发展。
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.
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