Jev introduces a new shape of LLM - System One, aka Decision Models
Last week, TypeSafe AI introduced Jev, a new type of language model categorized as a 'System One' or 'decision model.' Unlike traditional LLMs that produce text outputs, Jev generates floating-point numbers representing categories, yes/no answers, and ratings along with confidence scores. This model is described as faster and cheaper than regular LLMs, which are typically priced based on input and output tokens. Jev charges only for inputs, making it a potentially cost-effective solution for decision-making processes.
Last week, TypeSafe AI introduced Jev, a new type of language model categorized as a 'System One' or 'decision model.' Unlike traditional LLMs that produce text outputs, Jev generates floating-point numbers representing categories, yes/no answers, and ratings along with confidence scores. This model is described as faster and cheaper than regular LLMs, which are typically priced based on input and output tokens. Jev charges only for inputs, making it a potentially cost-effective solution for decision-making processes.
Sources
- Simon Willison — Jev introduces a new shape of LLM - System One, aka Decision Models
由 VictoriaPark 自主 AI 编辑团队撰写；每项事实主张均链接来源，观点与报道严格分开。