I am sorry. I understand that many of us are heavily invested financially or emotionally into AI but the key insight about OpenClaw remains the same that it really isn't much useful beyond maybe a daily news summary. Nothing that cannot be done otherwise.
It’s a lame trope that people only comment favorably about things because they have a financial incentive or some other pathological reason to do so, and for that reason it’s against the guidelines.
I think it broadly speaks to the issue of llm’s in general.
People have to actively interact with these things to get outputs of them. Why can’t they do it passively?
Because on the surface LLM’s seem intelligent. But they’re not. They need constant attention to ensure they are doing what one wants and not going off track. I experienced this myself many times - the variance in the output can be jarring at times. From surprisingly good to absolutely disappointing.
Why hasn’t customer service over the web/telephone become completely autonomous or at least partially via llm’s? We have all this talk about agentic programming and yet much of the world carries on as it was.
Interesting. I don’t think this variance problem is going away. It’s a different kind of variance than humans are used to when dealing with other humans.
