内容来源：https://www.wired.com/story/sleeptime-compute-chatbots-memory/

内容总结：

睡眠时，人类大脑会对记忆进行筛选，保留重要内容并剔除无用信息。如今，人工智能领域正试图复现这一神奇机制。

美国租房福利平台Bilt近期部署了数百万个AI智能体，通过与初创公司Letta合作，这些智能体可运用"睡眠计算"技术，像人类一样在后台进行记忆整理。该系统能将对话内容分类存储：重要信息存入长期记忆库，常用数据则置于快速调用区。Bilt的AI工程师安德鲁·菲茨表示："只需更新一个记忆模块，就能让数十万个智能体同步升级行为模式。"

与传统语言模型受限于固定上下文窗口不同，这种新技术试图突破AI的记忆瓶颈。Letta首席执行官查尔斯·帕克指出："人脑会像海绵一样持续吸收信息，而现有语言模型长时间运行后会产生记忆混乱，最终只能重启重置。"

这家人工智能公司的技术源于其联合创始人此前开发的MemGPT开源项目，如今已发展为允许智能体进行自主背景学习的成熟系统。行业正掀起一场AI记忆革命：另一家技术公司LangChain首席执行官哈里森·蔡斯认为"记忆本质上是语境工程的核心"，其公司为AI智能体提供了从用户特征到实时体验的多层次记忆存储方案。

消费者端也传来进展：OpenAI今年二月宣布ChatGPT将具备记忆功能以提供个性化服务，但未透露具体实现方式。行业领军者强调透明度的重要性——Hugging Face首席执行官克莱姆·德朗格表示："不仅模型要开源，记忆系统更应保持开放。"

值得深思的是，Letta团队认为"遗忘能力"与"记忆能力"同等重要。当用户要求删除特定项目记忆时，智能体应当能追溯并改写所有相关记忆节点。这种对人工智能记忆机制的探索，令人联想到菲利普·迪克在《仿生人会梦见电子羊吗？》中描绘的科幻世界——虽然当前的语言模型尚未达到小说中复制人的智能水平，但其记忆的脆弱性已然呈现出惊人的相似性。

（本文根据威尔·奈特《AI实验室通讯》整理）

中文翻译：

睡眠时，人类大脑会对不同记忆进行分类，强化重要记忆的同时剔除无关内容。若人工智能也能实现这种能力呢？
为租户提供本地购物与餐饮优惠的公司Bilt近期部署了数百万个智能体，正是为了达成这个目标。该公司采用初创企业Letta的技术，使智能体能够从历史对话中学习并实现记忆共享。通过名为"睡眠时间计算"的处理流程，这些智能体会判定哪些信息需存入长期记忆库，哪些需留作快速调取之用。

"我们仅需更新单个记忆模块，就能让数十万个智能体的行为同步改变。"Bilt人工智能工程师安德鲁·菲茨解释道，"在对智能体上下文需要精细控制的场景中，这种机制极具价值。"他所说的上下文正是指推理阶段输入模型的文本提示。

大型语言模型通常只能在上下文窗口包含信息时实现"记忆"。若要让聊天机器人记住最近对话，用户必须手动将内容粘贴至对话框。多数AI系统处理上下文窗口的信息容量有限，超出限度就会导致数据处理能力下降，进而产生幻觉输出或逻辑混乱。相比之下，人脑不仅能归档有用信息，还能随时准确调取。

"人脑会像海绵般持续吸收新信息不断进化。"Letta首席执行官查尔斯·帕克指出，"而语言模型恰恰相反。若长时间循环运行，其上下文就会受到污染，导致系统偏离正轨，最终只能通过重置来修复。"

帕克与联合创始人莎拉·伍德斯曾开发开源项目MemGPT，致力于帮助大语言模型区分短期与长期记忆存储。通过Letta平台，二人将这套方法论扩展至智能体的后台学习机制。Bilt与Letta的合作属于AI记忆能力开发的前沿探索，这项技术有望提升聊天机器人的智能水平并降低错误率。据受访专家表示，记忆功能仍是现代人工智能的薄弱环节，直接影响着AI工具的智能水平与可靠性。

另一家改善AI智能体记忆能力的公司LangChain的联合创始人兼首席执行官哈里森·蔡斯强调："记忆是上下文工程的核心组成部分。"该企业为客户提供多种智能体记忆存储方案，涵盖从用户长期特征到近期体验的全维度记录。"记忆本质上是上下文的形态体现，"蔡斯表示，"AI工程师的主要工作就是为模型配置正确的上下文信息。"

消费级AI工具也在逐步克服记忆缺陷。今年二月，OpenAI宣布ChatGPT将存储用户相关信息以提供个性化体验——尽管未公开具体技术细节。Letta与LangChain使AI系统构建者能更透明地管理记忆调取过程。

"模型开源固然重要，但记忆系统的开放性更具意义。"AI托管平台Hugging Face首席执行官、Letta投资者克莱姆·德朗格如是说。值得玩味的是，Letta掌门人帕克暗示AI学会遗忘同样关键："当用户要求'清除某个项目的一切记忆'时，智能体应当能追溯并改写所有相关记忆节点。"

关于人工记忆与梦境的研究让我联想到菲利普·迪克的科幻经典《仿生人会梦见电子羊吗？》——这部启迪《银翼杀手》的颠覆性小说。虽然大语言模型尚未达到小说中反叛复制人那般惊艳，但它们的记忆似乎同样脆弱易碎。

本文节选自威尔·奈特《AI实验室》时事通讯，过往内容可点击此处查看。

英文来源：

During sleep, the human brain sorts through different memories, consolidating important ones while discarding those that don’t matter. What if AI could do the same?
Bilt, a company that offers local shopping and restaurant deals to renters, recently deployed several million agents with the hopes of doing just that.
Bilt uses technology from a startup called Letta that allows agents to learn from previous conversations and share memories with one another. Using a process called “sleeptime compute,” the agents decide what information to store in its long-term memory vault and what might be needed for faster recall.
“We can make a single update to a [memory] block and have the behavior of hundreds of thousands of agents change," says Andrew Fitz, an AI engineer at Bilt. "This is useful in any scenario where you want fine-grained control over agents' context,” he adds, referring to the text prompt fed to the model at inference time.
Large language models can typically only “recall” things if information is included in the context window. If you want a chatbot to remember your most recent conversation, you need to paste it into the chat.
Most AI systems can only handle a limited amount of information in the context window before their ability to use the data falters and they hallucinate or become confused. The human brain, by contrast, is able to file away useful information and recall it later.
“Your brain is continuously improving, adding more information like a sponge,” says Charles Packer, Letta’s CEO. “With language models, it's like the exact opposite. You run these language models in a loop for long enough and the context becomes poisoned; they get derailed and you just want to reset.”
Packer and his cofounder Sarah Wooders previously developed MemGPT, an open-source project that aimed to help LLMs decide what information should be stored in short-term vs. long-term memory. With Letta, the duo has expanded their approach to let agents learn in the background.
Bilt’s collaboration with Letta is part of a broader push to give AI the ability to store and recall useful information, which could make chatbots smarter and agents less error-prone. Memory remains underdeveloped in modern AI, which undermines the intelligence and reliability of AI tools, according to experts I spoke to.
Harrison Chase, cofounder and CEO of LangChain, another company that has developed a method for improving memory in AI agents, says he sees memory as a vital part of context engineering—wherein a user or engineer decides what information to feed into the context window. LangChain offers companies several different kinds of memory storage for agents, from long-term facts about users to memories of recent experiences. “Memory, I would argue, is a form of context,” Chase says. “A big portion of an AI engineer's job is basically getting the model the right context [information].”
Consumer AI tools are gradually becoming less forgetful, too. This February, OpenAI announced that ChatGPT will store relevant information in order to provide a more personalized experience for users—although the company did not disclose how this works.
Letta and LangChain make the process of recall more transparent to engineers building AI systems.
“I think it's super important not only for the models to be open but also for the memory systems to be open,” says Clem Delangue, CEO of the AI hosting platform Hugging Face and an investor in Letta.
Intriguingly, Letta’s CEO Packer hints that it might also be important for AI models to learn what to forget. “If a user says, ‘that one project we were working on, wipe it out from your memory’ then the agent should be able to go back and retroactively rewrite every single memory.”
The notion of artificial memories and dreams makes me think of Do Androids Dream of Electric Sheep? by Philip K. Dick, a mind-bending novel that inspired the stylishly dystopian movie Blade Runner. Large language models aren’t yet as impressive as the rebellious replicants of the story, but their memories, it seems, can be just as fragile.
This is an edition of Will Knight’s AI Lab newsletter. Read previous newsletters here.