Darren LI

In time, the ratio of human work lessens, eventually getting closer to full automation even in areas which require a human specialist—i.e., where small mistakes can have disastrous effects—but likely not without a human somewhere in the loop, especially in areas that are particularly unforgiving to mistakes, such as diagnoses, drug prescriptions,... See more

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.

The first is, LLMs generally will lose when they get displaced by a new and better technology.

我们看到了做AI Coding的三种方法,这三种方法对应三个挑战:

1/ 如何创造更强的上下文感知能力?

2/ 如何让AI Agent在端到端编码任务中做的更好?

3/ 有人押注于编码模型,这能否带来长期的差异化?

Using a new technology comes at a cost. If it’s 1979 and you’re Walt Disney Pictures, you’ve got no reason to explore the VCR. The existing system works great for you — and it works great for your audience. You can always find a movie theater willing to show your movies, your audience is happy to be seen entering that cinema, and the bank gladly... See more