EngramLab 联合创始人将在 Fireworks Forge 谈智能体原生记忆
What if agents remembered things in their weights as well as their context? @realJessyLin, Co-found...
精选理由
如果你在做智能体，这个思路挺有意思：把记忆写进权重而不是全塞上下文里，可以去听听她怎么讲。
Fireworks AI 宣布 EngramLab 联合创始人 Jessy Lin 将在 11 月 3 日于旧金山举行的 Fireworks Forge 活动上演讲，主题是如何构建具备原生记忆的智能体。演讲核心问题之一是：智能体除了依赖上下文窗口之外，能否把信息存进模型权重里作为长期记忆。该活动为线下形式，报名链接已随推文公布。
原文 · Fireworks AI
What if agents remembered things in their weights as well as their context? @realJessyLin, Co-found...
What if agents remembered things in their weights as well as their context? @realJessyLin , Co-founder of @EngramLab , speaks at Fireworks Forge on building agents with native memory. Join us Nov 3 in SF: bit.ly/forgex 💬 1 🔄 1 ❤️ 2 👀 605 📊 2 ⚡
