跳到正文
原文
testingcatalog· @testingcatalog · X·· 4 小时前AI 评分59

Articul8 发布可接入 AI 智能体的决策模型 Bivia

AI 导读

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%。

正文 · 原文

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