Comment by PorciiVorbesc
5 hours ago
Sorry, it's not my job to provide for you the things that you demand from me at your whims, because the original comment I replied to with LLM data also did not bring peer-reviewable information as proof that COSMIC is a TOP 5 DE, and yet you did not demand proof from them in that case. Why is that?
Did you just blindly trust the opinions of others on this topic, and yet I'm the one who has to provide peer-reviewable data for you to back-up mine? Sorry, I'm not your unpaid lackey. Try to formulate a better (counter)argument for why their baseless opinion is right, but my LLM backed up opinion is wrong, if you wish for a even-footed good-faith argument.
I ask them for the same source (and looks like they provided it), your comment wasn't special. LLMs however are especially less trustworthy, that's why. It's not my job to educate you on why they are, as you say, and why people aren't trusting your comments.
>I ask them for the same source (and looks like they provided it)
I also saw it now. That blog is not a representative ground truth, but just another opinion piece, which I can respect as an opinion of the blog's user base, but I can't take as an accurate real world statistic, same how aggregate opinions you read on HN are not representative of the actual real world.
I hope you can understand my PoV. You can also disagree if you want, but you'll need to bring something more than "that's wrong because LLMs sometimes hallucinate" as proof that Gemini's data is wrong in this case.
In theory if you brought a better source than that person then I'd agree with you, but,
> you'll need to bring something more than "that's wrong because LLMs sometimes hallucinate" as proof that Gemini's data is wrong in this case.
actually I can say it's wrong or likely to be wrong especially if it doesn't cite the sources it uses. And if it does, then just paste the sources here instead of the LLM output. It is also unknown where it got the info and as someone else said, you ask it two different times and it gave two different answers, thus it is unreliable.