Live data from Hacker News

Exploring the "Dario and Amanda" Prompt

alec.is

21–22 of 22 posts

Re: Exploring the "Dario and Amanda" Prompt

#21
post #19
post #2

The raw runs are useful, but plausibility alone seems like a weak way to distinguish memorization from hallucination. I’d be curious to see a control set using random name pairs and the same number of trials. Then you could compare how often rare names, exact phrases, dates, or other specific details recur across fresh sessions. If “Dario and Amanda” produces stable, uncommon fragments while the controls only produce…

The content is hallucinated. LLM training doesn’t lend itself to easy training corpus document retrieval in that way. It’s not impossible to get segments nearly verbatim on a small model with temperature at 0 and a unique starting prompt for continuation, but that’d be more of a one-off on a carefully crafted prompt. It has been done, but in the “researchers show it’s possible to get something verbatim”, not “retriev…

This is a fascinating take. I love the idea of trying to scrub out the confabulated fills in a Mad Libs book and determining the original narrative being told.

It seems this narrative is filled with anxiety, fear and stress.

Re: Exploring the "Dario and Amanda" Prompt

#22
post #7

Wow especially the last one doesn’t look like a hallucination. It’s very distinct, untypical, specific, both in form and content. It’s even a running joke and a huge annoyance by now that it’s very hard to get AI to produce text that doesn’t sound generic. I write a lot and often ask Claude to fill in the blanks or expand a draft as if in my own voice, and the result is rarely satisfactory, even though he has access…

[dead]
Post reply on HN