Re:Yes-rs: A fast, memory-safe rewrite of the classic Unix y...
by lynx97 on Tuesday May 27, 2025 @03:14AM
(#44104638)
LLMs slurp up a lot of trolling and typical tech sarcasm through its training data. IMO a reason for "hallucinations".
[ Parent
| on HN ]
Re:Yes-rs: A fast, memory-safe rewrite of the classic Unix y...
by alpaca128 on Tuesday May 27, 2025 @03:46AM
(#44104773)
That depends on how you define hallucinations, I'd say AI repeating its training input is doing exactly what it's made for. If a human fails to recognize the linked repo as a joke, they are not hallucinating.