Re:Even 'uncensored' models can't say what they want
by llmmadness on Monday April 20, 2026 @06:43PM
(#47842022)
We started with a Polymarket project: train a Karoline Leavitt LoRA on an uncensored model, simulate future briefings, trade the word markets, profit. We couldn't get it to work. No amount of fine-tuning let the model actually say what Karoline said on camera. It kept softening the charged word.
[ Parent
| on HN ]
Re:Even 'uncensored' models can't say what they want
by Lucasoato on Monday April 20, 2026 @07:57PM
(#47842809)
Not even the most unleashed models can utter the words of today’s politicians, I don’t know if this says more about the current technology or the people in charge.
Re:Even 'uncensored' models can't say what they want
by amenhotep on Tuesday April 21, 2026 @12:06PM
(#47850736)
I would suggest it says primarily that mimicking people's voices in meaningful ways is still far beyond LLMs and particularly small LLMs, but also more insurmountably that the prompt for Leavitt herself contains many tokens that the LLM prompt absolutely doesn't
Such as the values of the bets her own entourage has placed
Re:Even 'uncensored' models can't say what they want
by throwawaypath on Tuesday April 21, 2026 @01:43PM
(#47851993)
Or the training data being too PC, "inclusive", effeminate, etc.
Re:Even 'uncensored' models can't say what they want
by subscribed on Wednesday April 22, 2026 @05:14AM
(#47861037)
"too effeminate"? I'm trying to understand what you're meaning by it and what the example of the excluded data would be.
Mind you, I didn't go through The Pile yet, need ot make some disk space first, so I can't even say if your "accusation" is correct.
Re:Even 'uncensored' models can't say what they want
by suburban_strike on Wednesday April 22, 2026 @04:15PM
(#47868722)
Reasoning by emotional manipulation rather than facts, data, or logic.
Re:Even 'uncensored' models can't say what they want
by throwawaypath on Thursday April 23, 2026 @06:31PM
(#47883045)
Or if it says more about the training data being too PC, "inclusive", effeminate, etc.
Re:Even 'uncensored' models can't say what they want
by gnabgib on Thursday April 23, 2026 @06:32PM
(#47883058)
Why are you trying this comment again? https://news.ycombinator.com/item?id=47851993
Re:Even 'uncensored' models can't say what they want
by throwawaypath on Thursday April 23, 2026 @08:04PM
(#47883852)
My original comment was flagged.
Re:Even 'uncensored' models can't say what they want
by conorcleary on Monday April 20, 2026 @08:05PM
(#47842882)
Trumps are advising the board of both of those gambling houses
Re:Even 'uncensored' models can't say what they want
by justinc8687 on Monday April 20, 2026 @08:38PM
(#47843143)
My favorite Hacker News comment in a while!
Re:Even 'uncensored' models can't say what they want
by pgsandstrom on Tuesday April 21, 2026 @04:40AM
(#47846217)
Could you break it down for someone who isnt in the know?
Re:Even 'uncensored' models can't say what they want
by datsci_est_2015 on Tuesday April 21, 2026 @01:52PM
(#47852087)
“We used LLM technology, which is great at parroting content, to attempt to predict what the US president’s spokesperson would say at their next conference.
We used that as input for ~gambling~ purchasing a position on a prediction market, which has been popularized recently in part due to its ability to circumvent gambling regulations.
However, even the LLM couldn’t parrot the words of the spokesperson. The implication is that the spokesperson speaks so outrageously that even an uncensored LLM couldn’t parrot their words.”
Re:Even 'uncensored' models can't say what they want
by WithinReason on Wednesday April 22, 2026 @02:09AM
(#47859697)
It's a direct quote from TFA