Articul8 发布可接入 AI 智能体的决策模型 Bivia
Articul8 发布决策模型 Bivia,可连接至 AI 智能体,并在置信度较低时暂缓决策。它支持结构化回复和多模态输入,可结合任务上下文在执行中途使用;当前价格为每百万输入 token $0.042,不提供订阅方案。原文指出,单步准确率达到 95% 时,智能体完成 20 步任务的概率仅约 36%。
Articul8 launched Bivia, its own decision model that can be connected to AI agents and hold back when confidence is low.
> Bivia weighs each decision against the goal of the whole task, instead of judging each step on its own.
> It supports structured replies and can be used by AI agents mid-step.
> It is multimodal and was specifically trained on active production workflows.
> Agents can include context from the task they are running along with each question.
> Bivia currently costs $0.042 per million input tokens with no subscription.
Small mistakes add up over long tasks. At 95% accuracy per step, an agent finishes a 20-step task only about 36% of the time.
来源:testingcatalog · x.com