随着模型能力的提升，智能系统的行为将主要取决于提供给LLM的context。其核心在于，如何基于已有的memory（上下文历史）构建合理的context送给LLM。所以，context/memory/harness成为与LLM能力独立的一极。如何更低成本、更高准确率提取，就成为Agent技术的关键。memory将成为agent的核心组件。
もっと見る
In 2024 the question was: which LLM do we use?
In 2025 the question is: how do we make agents actually work in production?
In 2026 the question will be: which context layer are we building on?
Here is why that shift is already underway:
もっと見る
