alt Hacker NewsYou have to learn to use your tools, not try whatever intuitively made sense to you at first (expecting the tool to do all the work) and then whining on Hacker News when it doesn’t work out for you.
Replies
To be fair, isn't the hypothetical promise of LLMs that the tool does all the thinking for you? If the AI companies are saying "delegate all your thinking", and then people delegate their thinking and it doesn't work out well, isn't that partially on the people overselling the capabilities? People are going to naturally benchmark on the promises. If these AI companies would admit it's just another tool instead of pretending we're in the singularity and doing a new stunt daily we wouldn't be dealing with all this.
I’m terribly sorry on their behalf. I hope the expression of their experience has not hurt Claude’s feelings (IPO valuation). Won’t happen again.
the whole selling point of these tools is they do the work for you
Incredibly dismissive of the parent comment. They made a comment explaining their usecase, and issues with the tool, which you just labeled as whining. Is this not a discussion board to talk about things? Is expressing issues with a use case you found now just considered whining on HN?
The parent commenter was trying to learn how to use the tool. Perhaps he could've used it better, but like you said, what may have worked was not necessarily the intuitive approach.
The parent comment also changed his approach, and AI worked for him to test out changes. That's not expecting the tool to do all the work, he's actually agreeing with you that "expecting the tool to do all the work" is a misstep.
This part is obviously their fault and they need to use their tools better:
> others dumping their raw AI output at me
Sheesh.
AI can not fail. It can only be failed. AI can not have limitations. Only the user can be limited.
We're reliving the early day Google era. It's an objectively simple tool to use, but some people just refuse to put any effort to learn.
I'm thinking the issue is probably that LLMs/harnesses are too easy to use? It crossed the thin line between magic and tooling and blur the mental model. If Claude Code were as hard to use as, say, ComfyUI, perhaps there would be less programmers having absurd expectation of it.