AI hallucinations are getting worse – and they're here to stay

AI is becoming that problematic tenant in a building, who presented well, and had great references, but is now bumming money from everbody, stealing peoples mail and reading before putting it back,cant pat there power bill, and wanders around talking to squirls We should build some sort of half way house, where the AI's can get therapy and some one to keep them on there meds, and do the group living thing till they, maybe, can join society. The last thing we need is some sort of turbo charged A+List psycho beaming itself into everybodys lives, but hey whatever! right!, people got to do what people got to do, and part of that is shrugging off all the hype and noise. I just keep doubling down on reality, it seems to come naturaly :)

&gt; But [&quot;hallucination&quot;] can also refer to an AI-generated answer that is factually accurate, but not actually relevant to the question it was asked, or fails to follow instructions in some other way.<p>No, &quot;hallucination&quot; can&#x27;t refer to that. That&#x27;s a <i>non sequitur</i> or non-compliance and such.<p>Hallucination is quite specific, referring to making statements which can be interpreted as referring to the circumstances of a world which doesn&#x27;t exist. Those statements are often relevant; the response would be useful if that world did coincide with the real one.<p>If your claim is that hallucinations are getting worse, you have to measure the incidences of just those kinds of outputs, treating other forms of irrelevance as a separate category.

Of course they&#x27;re here to stay. LLMs aren&#x27;t designed to tell the truth, or to be able to separate fact from fiction. How could they, given that their training data includes both, and there&#x27;s no &quot;understanding&quot; there in the first place? Naturally, the most straightforward solution is to redefine &quot;intelligence&quot; and &quot;truth,&quot; and they&#x27;re working on that.

I had an interesting one yesterday where I was building out some code on the Unreal engine and I gave o4-mini-high links to the documentation, a class header, and a blog with an example project.<p>I asked it to create some boilerplate and it presented me with a class function that I knew did not exist; though like many hallucinations it would have been very beneficial if it did.<p>So, instead of just pointing out that it didn&#x27;t exist and getting the usual &quot;Oh you&#x27;re right, that function does not exist so use this function instead&quot;, I asked it why it gave me that function given that it has access to the header and an example project. It doubled down and stated that the function was in the header and the example project, even presenting a code sample it claimed was from the example project with the fake function.<p>It felt like a step up from the confidently incorrect state I&#x27;d seen before to a level where if it weren&#x27;t for the fact that I&#x27;m knowledgeable enough about the class in question (or my ability to be able to check) then I&#x27;d possibly start questioning myself.