News for hackers. Stuff that matters.
Re:AI Hallucinations: Why Large Language Models Make Things ... by jojobas on Wednesday December 04, 2024 @10:25PM (#42324584)
There is no source of truth for dressage competition results, these are accepted as jury preference judgement.

There are plenty of matters where there is such a source of truth, and LLMs don't know the difference.

Re:AI Hallucinations: Why Large Language Models Make Things ... by mdp2021 on Thursday December 05, 2024 @02:37AM (#42325881)
> There is no source of truth

There is no «source of [_simple_] truth» for complex things, but there are more (instead of less) objective complex evaluations.

Note that this is also valid for factual notions: e.g., "When were the Pyramids built?".

Re:AI Hallucinations: Why Large Language Models Make Things ... by namaria on Thursday December 05, 2024 @02:55AM (#42325965)
Ancient Egypt chronology is a poor example of determined knowledge.

We do not know in fact exactly when (which?) Pyramids were built, there are large margin of errors in the estimates.

Re:AI Hallucinations: Why Large Language Models Make Things ... by mdp2021 on Thursday December 05, 2024 @03:19AM (#42326094)
That was my point: answering that question is a more complex evaluation than others. In lower percentiles you may have "what is in front of you" and in upper percentiles you may have "how to fix the balance of power in the Pacific" - all more or less complex evaluations.

I said, "Not even factual notions are trivial, e.g. "When has this event happened" - all have some foundational ground of higher or lower solidity".

Re:AI Hallucinations: Why Large Language Models Make Things ... by namaria on Thursday December 05, 2024 @03:39AM (#42326204)
Right, I misread your comment. Sorry!