I really like pi and have started using it to build my agent. Mario's article fully reveals some design trade-offs and complexities in the construction process of coding agents and even general agents. I have benefited a lot!

I am also Chinese and AI user. Manus is excellent, and it's hard to find a rival when it comes to making PPTs. The effect of wild search is exaggerated. The hype from official accounts is one thing, and the overwhelming scam comments on social media are another; neither is accurate. It has been almost a year. If Manus were really as simple as just getting Open Manus up and running, we should have seen many similar products. But unfortunately, there's only one Manus.

While embeddings are generally not required in the context of code, I am interested in how they perform in the legal and regulatory domain, where documents are substantially longer. Specifically, how do embeddings compare with approaches such as ripgrep in terms of effectiveness?

Not long ago I came across this book in an HN thread about AI and the future. The moment I saw the title, I knew I had to read it. Crypto, AI, collective intelligence — it hits all the right notes for me.

I'm a beginner user. My current agent is built using Java. I'm hesitant whether to use Python to call the api for evaluation or to introduce some tools into the Java project for evaluation, such as those related to OpenTelemetry.