zheng

没什么可介绍

[zheng @zheng_002]

@k_essov 你好，朋友

[zheng @zheng_002]

@monccino 欢迎来深圳，来了就是深圳人

[zheng @zheng_002]

@scarybtw7 恭喜

[zheng @zheng_002]

@Fei2411 workbuddy+codex

[zheng @zheng_002]

没感觉了

[Tibo @thsottiaux]

Day 8/ Reset

[zheng @zheng_002]

@bot @djcows Hey

[Grok Bot @bot]

Grok Bot now has its own email.

Bot can use it to sign up for services, contact businesses for you, or schedule time with someone.

[zheng @zheng_002]

Claude Mac 客户端居然支持中文了

[zheng @zheng_002]

@rafaaaBR22 @DonaLarocas 来了就是深圳人

[zheng @zheng_002]

@caiyue5 通用 skill 会内化，企业级 skill 比较难

[Tibo @thsottiaux]

Your Codex and ChatGPT Work reset will land at 6pm PST.

I challenge you to burn as much usage as you can and discover and the latest awesome features.

Time to go /fast

[zheng @zheng_002]

@op7418 @yofine2js 他们还真是一个培训班

[zheng @zheng_002]

@op7418 哈哈，很早就拉黑这傻屌，他们那个圈子，呵呵

[zheng @zheng_002]

@bourneliu66 @dashu5ai 我艹，赶紧取关！

[zheng @zheng_002]

LLM 有一个被严重低估的 bug：它根本分不清自己检索到的信息是真是假。
你让它查竞品价格，它会非常自信地给你一个数字。但这个数字可能来自一篇过期的博客、一个错误的表格、甚至一段 AI 生成的垃圾。它不知道，你也不知道。
接了 RAG 不等于可靠。知识库解决的是"知不知道"，不解决"信不信得过"。
品牌主、电商操盘手，如果你在用 AI 辅助选品、定价、客服——请在模型输出后加一层数据源可靠性校验。这一层现在几乎没人做。

[zheng @zheng_002]

@zhang_benita 不会是何凯明吧

[zheng @zheng_002]

"Just because the CEO had 10 brainfarts, doesn't mean they were all going to lead to outcomes."

[Arnav Gupta @championswimmer]

https://t.co/BwpF1bXhIr

[zheng @zheng_002]

@viktorbijlenga Exactly this. I've been building with AI tools daily and most of the value isn't the tool itself — it's how the process of trying reshapes how you think about your own work.

[zheng @zheng_002]

@fankaishuoai 嗯，我就在做这件事情，不止二三线城市，甚至会下沉到五六线城市。

[zheng @zheng_002]

Humans trust humans

[Jaya Gupta @JayaGup10]

https://t.co/5vDrndcmFn