Hacker News Reader

Comment by extr0pian | Hacker News Reader

> when we interact with an AI, we hallucinate the person on the other side of the interaction. Those hallucinations are far more common and far more consequential than any AI-generated "hallucinations" (these are more properly called "errors" or "defects").

I recently used Claude to study for a technical exam. I had uploaded the official certification guide to Claude and instructed it to answer my questions using only the guide and to cite it's sources from the book when it provided answers. I was using Fable when it was free w/ the pro plan and I was genuinely impressed at how it could explain things when a concept was unclear to me.

I did pass the exam, partly due to this study method. Admittedly, once I passed, I caught myself thinking that I should tell Claude that I passed and then felt embarrassed with myself for thinking that.

View on HN

I don’t think it’s that silly to tell Claude you passed. That feedback is useful context for that chat session; and could theoretically be used to improve future models.

Feedback is one thing, but another is complete memory. I used to stop talking in a thread once gpt solved my issue.

But then it would bring it up again in another thread, treating it as an active issue.

So now I always close with "thanks, that worked. Don't reply"

I've encountered this too for home lab projects. I had planned on implementing OPNsense in a VM, then realized it was adding too much complexity and bailed on it.

Later in separate chats about my homelab, the LLM made assumptions that I had already implemented OPNsense in a VM and it was actively running. I think it "assumed" that I had implemented it when I stopped responding in that thread.

You're missing the fact the they didn't have this in mind, and thought of it as sharing a positive result with a study partner.

Exactly this. My first impulse was along the lines of sharing a positive result with a study partner. I did eventually tell it I passed the exam so it would stop providing responses with the assumption I was still working on that exam.

I think a better approach would be to use the objective built-in feedback, like the thumbs up button in Gemini.

The technology is there to assist you. It can provide valuable feedback to you about what aspects of your studying were particularly productive or less so based on your test results. There is real meaning to developing this kind of interaction with an object, no different than how children use dolls to develop prosocial behaviors.

The doll never learns, though.

I am talking about the value to the user, who is the one 'hallucinating,' not the inanimate object, as that was the concern of note in the parent comment.

Interesting, I do that and haven't really thought embarrassed about it. I consider it akin to putting away tools once I'm done with them.

Likewise, speaking collaboratively or capturing emotion ("We did it!") would just align with any ongoing interactive and/or personal context of the thread.

I've done this despite also feeling silly about it, but then was surprised to get value from the response. Like something I didn't think about or would have otherwise forgotten to do.

So now I do it regularly.

Reply on news.ycombinator.com