Hacker News Reader

When I tell a human to analyze the data, I sure don't expect them to interpret it as "write code to graph it to a screen you can't see". You found the problem but glossed right over it.

> misusing the tool and then pretend that it doesn't work

It was told to analyze and then it did a bad job of analyzing. I don't care if an LLM expert expects this already, it's worth pointing out to everyone else. It's not PEBKAC.

View on HN

If a user misunderstands the purpose and value of a tool, this is PEBKAC.

The tool doesn't succeed at a reasonable task that humans can do. That's not PEBKAC, and warning people about it is a good thing.

This type of analysis is not outside the purpose of the tool. You're making excuses at this point. Do you really think it would be wrong to add that capability in the future?

It's a technical limitation, one that is far from obvious.

I think you think the llm is a magic box with an intelligent being inside that can magically do whatever you want it to, somehow. It is software. It has capabilities and limitations. Learn them, and use it appropriately. Or don't, you don't have to use it. But don't expect it to just do whatever you think it should do.

> It has capabilities and limitations. Learn them, and use it appropriately.

THAT IS THE POINT OF THE ARTICLE

If you can't figure that out, don't insult me.

Reply on news.ycombinator.com