Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Morde P0 proposes an evidence-gated Agent delivery loop

AI summary

The author outlines Morde P0, a proposed minimal workflow in which one Agent handles one repository-scoped bug or request and returns a pull request for human review. The design separates execution from delivery decisions, requires evidence tied to the candidate commit and runtime environment, and uses persistent state to prevent duplicate external actions after interruptions. The author also warns that the described Y Combinator case does not show that teams universally skip code reading or human review.

In-depth insight

Morde P0 offers a concrete design for keeping Agent execution, verifiable evidence, authorization, and human merge approval within one delivery loop.

最近看了 Lauren Tan 在公开演讲之后,受益匪浅。自己也变成一个grok bot 的重度用户,只需要告诉他我要干嘛,最后都能收获一个很不错的结果。自己也做一个叫morde的类似产品,下面分享一下最近的收获。

1. 从 Lauren 学什么:先缩短验证,再增加并行

1.1 让 Agent 真正运行应用,证据回到还在讨论问题的地方

在 Y Combinator 的《The Rise of AI Coworkers》演示段落,Lauren 在与同事讨论的 Slack 线程里发了一段 X 视频,问 Potato 能否支持类似的功能。Potato 调起 Cursor 云 Agent,后者在自己的虚拟机里运行应用、制作原型,视频和截图回到原线程。团队继续在同一个地方讨论实际效果。Lauren 描述的是这一个案例里的评审方式,不能据此推断团队所有改动都不读代码、不做人工复核。

我觉得值得抄的不是聊天窗口,也不是 Bot 数量,而是两次交接:用户不用把讨论手动搬进 IDE;工程结果也没有停在执行环境里。收到结果的人能看到刚才那件事做成了什么样。这比一条「已修复」省时间,也给继续追问留了上下文。

#Morde#DSH#Host Runtime#Cursor#Potato#Noodle#P-Stack#Codex

Original · 16 min readRead the original
Group chat

No comments yet. Start the conversation.