AgentGPT: 让AI代理在浏览器中自主运行 🤖

🔗 原文链接： https://reworkd.ai/blog/Understandi...

⏰ 剪存时间：2023-09-04 16:22:33 (UTC+8)

✂️ 本文档由飞书剪存一键生成

AgentGPT: Autonomous AI in your browser 🤖

The invention of the Generative Pre-trained Transformer (GPT) is one of the recent decade's most important advancements in AI technology. The GPTs powering today's Large Language Models (LLMs) demonstrate a remarkable ability for reasoning, understanding, and planning . However, their true potential has yet to be fully realized.​

生成预训练转换器（GPT）的发明是近十年来AI技术最重要的进步之一。为当今的大语言模型（LLM）提供动力的GPT展示了非凡的推理、理解和规划能力。然而，它们的真正潜力尚未完全实现。​

At Reworkd , we believe that the true power of LLMs lies in agentic behavior . By engineering a system that draws on LLMs' emergent abilities and providing an ecosystem that supports environmental interactions, we can draw out the full potential of models like GPT-4. Here's how AgentGPT works.​

在Reworkd，我们相信LLM的真正力量在于代理行为。通过设计一个利用LLM紧急（新兴）能力的系统并提供支持环境相互作用的生态系统，我们可以充分发挥GPT-4等模型的潜力。以下是AgentGPT的工作原理。​

LLMs have a lot of limitations.

The main products shipping LLMs are chatbots powered by Foundation Model - Techopedia .

If you have any familiarity working with OpenAI's API, a common formula you might use for chatting with the model may include:​

运输LLM的主要产品是由Foundation Model-Techopedia提供支持的聊天机器人。​

如果你熟悉OpenAI的API，你可以使用一个通用的公式与模型聊天，包括：​

•
Taking the user's message.​

•
Adding a list of chat histories.​

•
Sending the chat history across the API to retrieve a completion.​

This method works fine when the scope of conversations is small; however, as you continue adding new messages to the chat history, the size and complexity of completions balloons , and you will quickly run into a wall: the dreaded context limit.​

•
获取用户的消息。​

•
添加聊天记录列表。​

•
跨API发送聊天记录以检索完成。​

当对话的范围很小时，这种方法工作得很好；但是，当您继续向聊天记录添加新消息时，完成的大小和复杂性会膨胀，您将很快遇到一堵墙：可怕的上下文限制。​

A context limit is the maximum number of tokens (a token usually represents a single word) that can be input into the model for a single response. They are necessary because the computational cost as we add additional tokens tends to increase quadratically . However, they are often the bane of prompt engineers.​

上下文限制是单个响应可以输入到模型中的最大标记数（标记通常代表单个单词）。它们是必要的，因为我们添加额外标记时的计算成本往往会呈二次增长。然而，它们通常是提示工程师的克星。​

One solution is to measure the number of tokens in the chat history before sending it to the model and removing old messages to ensure it fits the token limit. While this approach works, it ultimately reduces the amount of knowledge available to the assistant.​

一种解决方案是在将聊天历史记录发送到模型之前测量聊天历史记录中的标记数量，并删除旧消息以确保其符合标记限制。虽然这种方法有效，但它最终会减少助手可用的知识量。​

Another issue that standalone LLMs face is the need for human guidance. Fundamentally, LLMs are next-word predictors, and often, their internal structure is not inherently suited to higher-order thought processes, such as reasoning through complex tasks. This weakness doesn't mean they can't or don't reason. In fact, there are several studies that shows they can. However, it does mean they face certain impediments. For example, the LLM itself can create a logical list of steps; however, it has no built-in mechanisms for observation and reflection on that list.

独立LLM面临的另一个问题是需要人类指导。从根本上说，LLM是下一个词的预测器，通常，它们的内部结构并不天生适合更高级的思维过程，例如通过复杂任务进行推理。​

这一弱点并不意味着他们不能或不推理。事实上，有几项研究表明他们可以。然而，这确实意味着他们面临某些障碍。例如，LLM本身可以创建一个合乎逻辑的步骤列表；然而，它没有对该列表进行观察和反思的内置机制。​

A pre-trained model is essentially a "black box" for the end user in which the final product that is shipped has limited to no capability of actively updating its knowledge base and tends to act in unpredictable ways . As a result, it's hallucination -prone.

预训练模型本质上是最终用户的“黑匣子”，其中交付的最终产品被限制为没有主动更新其知识库的能力，并且倾向于以不可预测的方式行动。因此，它容易产生幻觉。​

Thus, it requires a lot of effort on the user's part to guide the model's output, and prompting the LLM itself becomes a job on its own. This extra work is a far cry from our vision of an AI-powered future.​

因此，用户需要花很多精力来指导模型的输出，提示LLM本身就成了一项单独的工作。这额外的工作与我们对AI驱动未来的愿景相去甚远。​

By providing a platform to give LLMs agentic abilities, AgentGPT aims to overcome the limitations of standalone LLMs by leveraging prompt engineering techniques, vector databases, and API tooling. Here’s some interesting work that is being done with the agent concept:​

AgentGPT通过提供一个平台来赋予LLM真正的能力，旨在通过利用提示工程技术、向量数据库和API工具来克服独立LLM的局限性。​

以下是代理概念正在做的一些有趣的工作：

AgentGPT: 让AI代理在浏览器中自主运行 🤖​

AgentGPT: 让AI代理在浏览器中自主运行 🤖