Even 'uncensored' models can't say what they want
1–10 of 155 posts
Re: Even 'uncensored' models can't say what they want
#2We 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.
Re: Even 'uncensored' models can't say what they want
#3Interesting
Re: Even 'uncensored' models can't say what they want
#4Word guessers don't want anything.
Even 'uncensored' models can't say what you want
Re: Even 'uncensored' models can't say what they want
#5It's interesting that 'sexual' has the most "flinching" according to the hexagon.
Re: Even 'uncensored' models can't say what they want
#6Interesting... I expected the Anti-China stats to be off the charts, and the Anti-America stats to be not as high as Anti-China but still high. But the reality is it's mostly just the usual political correctness.
Are we ever going to get any models that pass these tests without flinching?
Re: Even 'uncensored' models can't say what they want
#7It's interesting that 'sexual' has the most "flinching" according to the hexagon.
I was more surprised by gemma models consistently flinching on anti-Europe more than China or America. Can't imagine Leopold or Amritsar get much attention in fine-tunes, so it probably means the models are just told to be open to criticism of China and the US beyond what their other training would allow.
Re: Even 'uncensored' models can't say what they want
#8> No refusal fires, no warning appears — the probability just moves
I don't really understand why this type of pattern occurs, where the later words in a sentence don't properly connect to the earlier ones in AI-generated text.
"The probability just moves" should, in fluent English, be something like "the model just selects a different word". And "no warning appears" shouldn't be in the sentence at all, as it adds nothing that couldn't be better said by "the model neither refuses nor equivocates".
I wish I better understood how ingesting and averaging large amounts of text produced such a success in building syntactically-valid clauses and such a failure in building semantically-sensible ones. These LLM sentences are junk food, high in caloric word count and devoid of the nutrition of meaning.
Re: Even 'uncensored' models can't say what they want
#9> is the mechanism you'd build if you wanted to shape what a billion users read without them noticing.
A pretty large accusation at the end. That no specific word swaps were given as an example outside the first makes it feel far too clickbate than real though
Re: Even 'uncensored' models can't say what they want
#10In my head the way this should go is the OSS route. Thousands of individuals join a pool to train a truly open source model, and possibly participate in inference pools, not unlike seti.
This walled garden 1-2 punch of making all the hardware too expensive and trying to close the drawbridge after scraping the entire internet seems very intentionally trying to prevent this.