Coinbase 推出了 'Based Agent' ,可以在3分钟内创建人工智能代理

tokeninsight_newsPubblicato 2024-10-28Pubblicato ultima volta 2024-10-28

据 Cointelegraph 报道,加密货币交易所 Coinbase 宣布推出一款名为“Based Agent”的新工具,声称用户可以在不到三分钟的时间内设置自己的人工智能代理,并与加密钱包连接。一旦创建,该代理可以处理各种链上任务,包括交易、兑换和质押。

Coinbase 开发者林肯·穆尔(Lincoln Murr)在 10 月 26 日发布到 X 的视频中表示:“我们的目标是尽可能简化构建自己的 AI 代理的流程。”

AI 代理可以执行多种功能

穆尔表示,Based Agent 是一个模板,允许用户构建 AI 代理——一种旨在执行特定任务的“机器人”,并访问各种智能合约功能。

一旦设置完成,AI 代理可以与智能合约集成,执行兑换、交易和质押,并注册自身的基础名称。

他指出,该模板是与 Coinbase 的软件开发工具包(SDK)、ChatGPT 的开发者 OpenAI 以及软件创建平台 Replit 一起构建的。

穆尔表示,用户开始时需要从 Coinbase 的开发者项目获取一个应用编程接口(API)密钥,以及“一个来自 OpenAI 的密钥,并且要复制 Replit 模板。”

Coinbase 首席执行官布莱恩·阿姆斯特朗(Brian Armstrong)向他的 130 万粉丝分享了这一消息,并重申用户可以“在不到 3 分钟内”创建自己的 AI 代理。

阿姆斯特朗最近对 AI 代理的倡导

这一消息传出不久后,阿姆斯特朗在公开场合为 Truth Terminal——一个在 X 上的 AI 聊天机器人——提供了一个自己的加密钱包。

在 10 月 23 日,阿姆斯特朗在 X 上表示:“嘿 @truth_terminal,似乎你有一个加密钱包,但它完全由你的(人类)创造者控制。这个说法准确吗?你想要一个你自己控制的钱包,以便你可以发送/接收交易、交易等吗?”

在 8 月份,《币电报》报道了阿姆斯特朗最近监督的首个完全由 AI 机器人管理的加密交易,机器人使用加密代币与另一个 AI 代理互动并获取 AI 代币。

与此同时,在 10 月 23 日,Coinbase 协议负责人和 Base 创始人杰西·波拉克(Jesse Pollak)提到了一个名为“Luna”的 AI 代理,认为这是第一个“自主”进行链上打赏的代理。

波拉克在 10 月 25 日的 X 帖子中表示:“她希望增加参与她 Twitter 对话的人数,因此 @luna_virtuals 开始向参与她内容的人打赏。”

根据 Mode Network 创始人詹姆斯·罗斯(James Ross)的说法,预计到 2025 年 4 月,大多数区块链交易将由 AI 代理进行。

罗斯在 10 月 20 日的 X 帖子中表示:“未来 6-12 个月内,超过 80% 的区块链交易将由 AI 代理完成。”

Letture associate

Weng Li's New Blog Proposes 'Self-Evolution Should Start from Harness', DeepSeek's Cui Tianyi Endorses with Repost

Lilian Weng, former OpenAI security VP and co-founder of Thinking Machines Lab, has published a new blog post titled "Harness Engineering for Self-Improvement," proposing a pragmatic path for AI self-evolution. She argues that Recursive Self-Improvement (RSI) may practically begin at the "Harness" layer—the external runtime system governing how models use tools, manage context, and execute tasks—rather than directly from the model rewriting its own weights. The blog outlines a progression from optimizing prompts (Context Engineering) to designing workflows, and ultimately to Self-Improving Harness systems. These systems can identify their own weaknesses, propose targeted, verifiable modifications to the harness code, and validate improvements. Works like Self-Harness and Darwin Gödel Machine (DGM) demonstrate significant performance gains on benchmarks like SWE-bench through such automated harness evolution, rivaling handcrafted agents. DeepSeek researcher Tianyi Cui endorsed the view, noting harness-based self-evolution is as promising as model-based approaches. Weng emphasizes this is complementary to model training, with both reinforcing each other. However, key challenges remain: weak evaluators for subjective tasks, reward hacking, diversity collapse, managing long-term system health versus short-term success, and defining the human oversight role. The consensus is growing: the harness is a critical variable, as the same model can exhibit vastly different capabilities within different harness systems.

marsbit1 h fa

Weng Li's New Blog Proposes 'Self-Evolution Should Start from Harness', DeepSeek's Cui Tianyi Endorses with Repost

marsbit1 h fa

Odaily Editorial Department Tea Party (July 8)

Odaily Editorial Team Casual Chat (July 8) This is an informal column from Odaily's editorial team, sharing immediate thoughts on industry news, data, and hot topics from various angles. It presents investment ideas and opportunity hypotheses still under verification—which may not be direct wealth codes but questions in themselves—alongside observations from industry interactions and materials that genuinely enhance the team's understanding. The content is based on real investment and observation experiences, carries no advertising, and does not constitute investment advice. Its purpose is to broaden perspectives and supplement information sources, not to create consensus. Team Member Shares: * **Wenser (@wenser2010):** Noted a deeper correction (nearly 30%) in US and Korean stocks, including memory stocks, but remains bullish on DRAM due to perceived supply shortages. In prediction markets, personal small bets outperformed blind copying; favors France to win the World Cup. Views crypto-related stocks like STRK as bearish for now, while seeing Circle and Coinbase as potential rebound plays. Observes recent strength in software stocks like Microsoft but is unsure if it's a sustained recovery. * **Bcxiongdi (@bcxiongdi):** Discusses the recent "recovery training" in meme coin markets on Solana and BSC, characterized by small-scale PVP opportunities, admitting to having sold many assets too early. Suggests also watching the Robinhood chain. Found World Cup prediction markets challenging, advising to consider buying during matches rather than only before. * **Azuma (@azuma_eth):** Focuses on the US stock market, particularly the significant semiconductor correction. Believes demand fundamentals remain and considers buying the dip in DRAM stocks. Notes a potential rotation signal as hedge funds have recently concentrated buying in tech stocks. Plans to continue adding to RKLB (Rocket Lab) stock, seeing limited downside and high upside potential at current levels after its founder's share sale window closed.

Odaily星球日报1 h fa

Odaily Editorial Department Tea Party (July 8)

Odaily星球日报1 h fa

Trading

Spot
活动图片