Hacker News new | ask | show | jobs
by SonOfLilit 6 days ago
https://github.com/NousResearch/llm-abliteration
1 comments

well see my other comment. with all due respect to Teknium, perhaps he misspelled it.
first version...

curprev 22:29, 29 May 2025 ZeevoX talk contribs 2,320 bytes +2,320 Create page for "abliterate" Tag: added link

not very credible.

I wnt and read your other comments.

Except for the initial comment, they were aggressive and sometimes disrespectful claims that "the word is spelled ablation, here are some papers that use it" in response to people saying "yes, we know what ablation means, but GP is intentionally using a separate word 'abliteration' that is the accepted word for the kind of ablation he's talking about, see links to respectable sources using or defining it". I downvoted them because I feel the discussion would be more valuable and feel nicer to read without them, and you could just read any of the offered links before responding and save the trouble.

Is surely super agressive to outright downvote given evidence says otherwise but that’s fine I guess. Let’s drop it, apparently we’re not getting to mutually satisfying conclusion.
Is there any evidence that would change your mind?

The wiki "ablation" article you yourself linked dedicates a section to explain "abliteration".

Googling abliteration arxiv yields at least one page of papers that mention it in the abstract (all but one in the title too). I counted 9 unique papers.

If it was shown that all of these were posted after this discussion started, or by people related to the person you tried to correct, I would be convinced that abliteration is not a real word. But evidence keeps pointing otherwise, nnd you keep arguing with evidence that proves "ablate" is a word (to which we all agree), not evedence that proves "abliterate" isn't.

You did show evidence that it's a pretty new word (of course it is! it's a pretty new technique in a field that didn't exist before the first open source RLHF'd models were released in '23!), and indeed, this (different) wiktionary page contains its origin story from '24: https://en.wiktionary.org/wiki/abliterate#English

There’s no info who and why coined it. Ans statistics weighs in favour of what I try to convince you into, not against. So question is - why wouldn’t you drop? Are you an LLM perhaps… is hard to tell from text only but you act stubborn as one.
Huh? The wiktionary link I included links to (Failspy's message in) this 2024 discussion about how and when and why it was coined (by failspy): https://huggingface.co/posts/mlabonne/866788930457283#67196f..., as well as another one.

To your question, I am not a bot, my LinkedIn is in my profile if you want to know who I am.

I'm persisting because, I guess, I'm really confused by your own insistence, and feel curious to get to the bottom of the weird misunderstanding we must be having (maybe you're trying to argue something different than "user chmod775 intended to refer to 'ablation' and was mistaken to write 'Just put "uncensored", "abliterated", or "heretic" into search on huggingface/ollama/etc and pick any them' instead of 'Just put "uncensored", "ablated", or "heretic" into search on huggingface/ollama/etc and pick any them'?). And I have a lot of free time on a climbing vacation where my brain is too mushy to do anything more productive than talk to people on the interblags.