Comment on AI agents wrong ~70% of time: Carnegie Mellon study
Melvin_Ferd@lemmy.world 1 week ago😆 I can’t believe how absolutely silly a lot of you sound with this.
LLM is a tool. It’s output is dependent on the input. If that’s the quality of answer you’re getting, then it’s a user error. I guarantee you that LLM answers for many problems are definitely adequate.
It’s like if a carpenter said the cabinets turned out shit because his hammer only produces crap
davidagain@lemmy.world 1 week ago
You have an irrational and wildly inaccurate belief in the infallibility of LLMs.
You’re also denying the evidence of my own experience. What on earth made you think I would believe you over what I saw with my own eyes?
Melvin_Ferd@lemmy.world 1 week ago
Why are you giving it data. It’s a chat and language tool. It’s not data based. You need something trained to work for that specific use. I think Wolfram Alpha has better tools for that.
davidagain@lemmy.world 1 week ago
Because there’s a button for that.
This thing that you said… It’s false.
Melvin_Ferd@lemmy.world 1 week ago
There’s a sleep button on my laptop. Doesn’t mean I would use it.
I’m just trying to say you’re saying the feature that everyone kind of knows doesn’t work. Chatgpt is not trained to do calculations well.