Lee Ross 分享 Bot 自主操作的安全审查机制
How can you trust @Bots to operate autonomously?
How can you trust @Bots to operate autonomously?
你如何信任 @Bot 能够自主运行？
This is something we've carefully designed. First, we use an LLM to automatically review every action your bot takes. If anything is unexpected, it will ask for your approval.
这是我们精心设计的功能。首先，我们使用大语言模型自动审查你的机器人执行的每一项操作。如果有任何意外情况，它会请求你的批准。
But this isn't enough. We also have customizable rules to allow or deny actions. For example, I have bots that are connected to my X, Gmail, etc. I explicitly block any write/destructive actions and have it ask for my approval first.
但这还不够。我们还提供了可自定义的规则来允许或拒绝某些操作。例如，我有连接到我的 X、Gmail 等平台的机器人。我明确禁止任何写入/破坏性操作，并要求在执行前征求我的同意。
This is a good balance between YOLO mode and reviewing everything by hand. Although, we do support YOLO if you like to live dangerously!
这是在 YOLO（盲目）模式和手动审查一切之间取得的良好平衡。不过，如果你喜欢冒险，我们也支持 YOLO 模式！
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力