Darren LI

It’s delightful to have the freedom to Bring Your Own Client (BYOC): to choose your favorite application to interact with some data.

Embra was one of the first AI Agents startups. Today, we are renaming AI Agents to AI Commands, and narrowing our focus away from autonomous agents. While autonomous agents took off in popularity, we found they were often unreliable for work, inefficient, and unsafe. 🧵

In the traditional LangChain Agent framework (and the AutoGPT framework), the agent thinks one step ahead at a time. For a given state of the world it think about what its next immediate action should be, and then does that action.

6. Don’t start out with a DAO. A lot of our internal governance/decisions or interactions between members is not what you usually see, and I think community governance is extremely inefficient and makes no sense for most products. I think DAOs only make sense for a few small categories of products.

编程这项工作非常适合 AI 增强或替代 ,原因如下:

1/ 编码本质上要求工程师将问题分解成更小、更易管理的任务;

2/ 有大量现有的训练数据;

3/ 任务需要判断力和基于规则的工作相结合;

4/ 解决方案利用可组合的模块(比如开源软件库等);

5/ 在某些情况下,工作成果可以通过经验测试其正确性。这意味着可靠的 AI 编码工具可以提供可量化的价值。