How outdated information hides in LLM token generation probabilities

Re:How outdated information hides in LLM token generation pr... by ben_w on Sunday January 12, 2025 @05:23AM (#42672521)

Same way as we can: learning which sources are more trustworthy.

There's limits to how far you can go with this — not only do humans make mistakes with this, but even in the abstract theoretical it can never be perfect: https://en.wikipedia.org/wiki/Münchhausen_trilemma — but it is still the "how".

[ Parent | on HN ]

Re:How outdated information hides in LLM token generation pr... by fullstackwife on Sunday January 12, 2025 @06:07AM (#42672701)

for the last 25+ years we rather not learned, but trusted the top3 of SERPs. Every ranking algorithm will be gamed eventually

[ Parent | on HN ]

Re:How outdated information hides in LLM token generation pr... by ben_w on Sunday January 12, 2025 @11:23AM (#42674645)

I would say that we learned to trust the search engines; but otherwise I agree with you: every ranking algorithm will be gamed eventually.

(I wonder if giving an LLM content with intent to cause its users to spend money they didn't need to, would count as fraud, hacking, both, something else entirely?)

[ Parent | on HN ]