[HN Gopher] A tool that removes censorship from open-weight LLMs
___________________________________________________________________
A tool that removes censorship from open-weight LLMs
Author : mvdwoord
Score : 86 points
Date : 2026-03-06 14:27 UTC (8 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| greenpizza13 wrote:
| Never stopped to ask if they should...
| Alifatisk wrote:
| This is for local models right? I can't use it on, say my glm-5
| subscription connected to opencode?
| HanClinto wrote:
| Correct, local models only.
| ComputerGuru wrote:
| Reviews of the tool on twitter indicate that it completely nerfs
| the models in the process. It won't refuse, but it generates
| absolutely stupid responses instead.
| Animats wrote:
| Link?
|
| It's interesting that people are writing tools that go inside
| the weights and do things. We're getting past the black box era
| of LLMs.
|
| That may or may not be a good thing.
| noufalibrahim wrote:
| I believe that this is already done to several models. One
| that I've come across are the JOSIEfied models from Gokdeniz
| Gulmez. I downloaded one or two and tried them on a local
| ollama setup. It does generate potentially dangerous output.
| Turning on thinking for the QWEN series shows how it arrives
| at it's conclusions and it's quite disturbing.
|
| However, after a few rounds of conversation, it gets into
| loops and just repeats things over and over again. The main
| JOSIE models worked the best of all and was still useful even
| after abliteration.
| thegrim33 wrote:
| Whether or not the linked tool uses a good approach,
| manipulating models like you mention is already fairly well
| established, see:
| https://huggingface.co/blog/mlabonne/abliteration .
| kube-system wrote:
| I guess it's kind of like a lobotomy tool.
| sheepscreek wrote:
| I guess it proves you cannot unlobotomize a hole in the head.
| littlestymaar wrote:
| This is vibecoded garbage that the "author" probably didn't
| even test by themselves since making this yesterday, so it's
| not surprising that it's broken.
|
| Also, as I said in a top level comment, what this project wants
| to achieve has been done for a while and it's called Heretic:
| https://github.com/p-e-w/heretic
|
| (Not vibecode by a twitter influgrifter)
| quotemstr wrote:
| We will eventually arrive at a new equilibrium involving
| everyone except the most stupid and credulous applying a lot
| more skepticism to public claims than we did before.
|
| And yeah, doing stuff like deleting layers or nulling out
| whole expert heads has a certain ice pick through the eye
| socket quality.
|
| That said, _some_ kind of automated model brain surgery will
| likely be viable one day.
| dinunnob wrote:
| Hate to have to be the one to stick up for pliny here, but
| hes concerned about forcing frontier labs to focus more on
| model guardrails - he demonstrates results that are crazy all
| the time
|
| https://x.com/elder_plinius
| IncreasePosts wrote:
| I didn't use this tool, but I did try out abliterated versions
| of Gemma and yes, it lost about 100% of it's ability to produce
| a useful response once I did it
| halJordan wrote:
| Everyone says that abliteration destroys the model. That's the
| trope phrase everyone who doesn't know anything but wants to
| participate says. If someone says it to you, ignore them.
| littlestymaar wrote:
| Don't use this 2 days old vibe coded bullshit please.
|
| p-e-w's Heretic (https://news.ycombinator.com/item?id=45945587)
| is what you're looking for if you're looking for an automatic de-
| censoring solution.
| a2128 wrote:
| You're not just using a tool -- you're co-authoring the science.
|
| This README is an absolute headache that is filled with AI
| writing, terminology that doesn't exist or is being used
| improperly, and unsound ideas. For example, it focuses a lot on
| doing "ablation studies", by which it means removing random
| layers of an already-trained model, to find the source of the
| refusals(?), which is an absolute fool's errand because such
| behavior is trained into the model as a whole and would not be
| found in any particular layer. I can only assume somebody vibe-
| coded this and spent way too much time being told "You're
| absolutely right!" bouncing back the worst ideas
| creatonez wrote:
| > For example, it focuses a lot on doing "ablation studies", by
| which it means removing random layers of an already-trained
| model, to find the source of the refusals(?), which is an
| absolute fool's errand because such behavior is trained into
| the model as a whole and would not be found in any particular
| layer.
|
| That doesn't mean there couldn't be a "concept neuron" that is
| doing the vast majority of heavy lifting for content refusal,
| though.
| dinunnob wrote:
| Hmm, pliny is amazing - if you kept up with him on social media
| you'd maybe like him https://x.com/elder_plinius
| bigyabai wrote:
| If this qualifies as "amazing" in 2026 then Karpathy and
| Gerganov must be halfway to godhood by now.
| dinunnob wrote:
| I dont think anyone is going to dispute this
| bigyabai wrote:
| I just don't think many people will be "amazed" by their
| output, as you claim.
| dinunnob wrote:
| I just said pliny was amazing, fwiw - i like that hes
| hacking on these and posts about it. I rushed to defend,
| i wish more people were taking old school anarchist
| cookbook approaches to these things
| cess11 wrote:
| Smoke banana peel?
| EGreg wrote:
| Amazing as in his stuff actually works?
|
| I just hear him promoting OBLITERATUS all day long and trying
| to get models to say naughty things
| dinunnob wrote:
| Yeah but i think the philosophy is to show how precarious
| the guardrails are
| gavinray wrote:
| The parent comment makes no reference to or comment on the
| author of the README.
|
| It just says "the README sucks." Which, I'm inclined to
| agree, it does.
|
| LLM-generated text has no place in prose -- it yields a
| negative investment balance between the author and aggregate
| readers.
| robertk wrote:
| You don't know what you are talking about. Obviously refusal
| circuitry does not live in one layer, but the repo is built on
| a paper with sound foundations from an Anthropic scholar
| working with a DeepMind interpretability mentor:
| https://scholar.google.com/citations?view_op=view_citation&h...
| paradox460 wrote:
| It's not just a headache, it's bad
| measurablefunc wrote:
| This is another instance of avant-garde "art".
| PeterStuer wrote:
| Already censored for sharing on FB Messenger?
| ftkftk wrote:
| Didn't make it past the first paragraph of AI slop in the README.
| Have some respect for your readers and put actual information in
| it, ideally human generated. At least the first paragraph!
| Otherwise you may as well name it IGNOREME.
| SilverElfin wrote:
| Does anyone offer a live (paid) LLM chatbot / video generation /
| etc that is completely uncensored? Like not requiring doing any
| work except just paying for it?
| nomel wrote:
| Grok was one of the closest, with expected results: bad PR from
| the obvious use cases that come with little censorship.
___________________________________________________________________
(page generated 2026-03-06 23:00 UTC)