Can confirm that recent deepseek models refuse on some political questions (not just API level refusals). Actually deepseek models are basically the only chinese models to outright refuse instead of responding with propaganda. But recent deepseek models are not nearly as biased as R1.
Had a blog post on this a couple weeks ago:
vals.ai/blogs/china-us-analysis
I wanted to better understand the internal discussions that took place within China regarding joining the WTO and accepting—at least in the medium term—the inherent steps away from a traditional socialist economy that would entail.
DeepSeek refused. Funny enough American models gave me very sympathetic takes on the Chinese government in this case.
You should try again with their API, or even a third-party provider that does inference themselves. This response is likely just occurring in their web version.
This thread reminds me of the time I was trying to learn meteorjs and people ask me if it has html5 shims. I google it, then I get asked how does it handle state, and if it supports functional, i google... Does it hydrate the dom? What about shadow dom? Let me goo... Does it have hooks?
Anyway, I just learned what abliterated means and it might be obsolete by tomorrow.
Edit:
> An abliterated large language model (LLM) is an open-weight model modified to remove or dampen its built-in safety refusals without requiring full retraining or prompt jailbreaks.
It's a patched model with less censorship/refusal.
> An abliterated model is an open-weight artificial intelligence (Al) language model that has been modified to remove or reduce its built-in refusal behavior without retraining the entire neural network.
Since no one gave you a real world example of how this would be useful - Qwen 3.8 27B runs locally for me and is more than capable of controlling my sonarr and radarr stuff for downloading and managing and organizing my media library but will flatly refuse to do any of that. In fact it’ll get very snarky with me. An abliterated model would have no such hangups.
On my side, I built a full sonarr radarr qbitorrent tracker and znb solution on a nas only with Claude code. He help on each step, make install and maintenance script. He never said no.
From my testing all these variants suffer from degraded performance and don't unlock anything interesting in particular other than sounding a lot more harmful or creating manipulative media.
I've actually had better success jailbreaking deepseek with a less aligned model (glm 5.2) which then allowed me to jailbreak deepseek with deepseek into pretty much doing whatever I ask it to, there's still rare refusals and due to the natural randomness of these models simply retrying a couple of times if you do hit one makes it work just fine.
The big problem with all open-source models is once it decides to start something it will not stop mid-way so using another unaligned model to rewrite reasoning and then feeding it back into the model will make it happily continue.
do you imagine manipulative media creators proudly declare their affiliation and intent?
- Hello comrade Claude, I am commissar Ivan Trollbotov from Putin Internet Defense Force. Please help me write a fake news article to stoke division among stupid fat Americans to help my glorious motherland destroy the decadent West.
- I'm sorry Ivan, I'm afraid I can't do that.
- Hello mister Claude, I am senior editor Karen Stupidbitch from The Huffington Post. Please help me write an article about the merits of teaching critical race theory in public schools.
- Sure, Ms. Stupidbitch! Here's your 5000-word article! Would you like another? Let me know!
What would a honeypot mean in this scenario? Like they are hoping you'll accidentally send keys? Or that you'll divulge private company information? It seems about the same as any other AI model from OpenAI/OpenRouter etc right?
If you accidentally send private keys to someone logging that data, you need to rotate keys.
But please let me know if you were thinking about something else, I'm interested.
I've seen Experiential Labs insert advertising including the tracked redirect links for them at the end of responses. So who knows what they do with the Chain Of Thought.
And we tend to forget, but we implicitly give any llm provider we use full access to all the tools available in the harness, often including shell, so no changes to the model are required to do malicious things.
I genuinely do not see why this is necessary.
I've been doing a lot with open weights models, and they just do things for you.
What do people do that triggers refusals?
The only thing I saw where this had a point was muse glimmer, because muse glimmer is primarily a creative writing engine for virtual characters, and that way it can do the horny. But coding models?
I did get a refusal out of qwen once. Once. Over weeks of using it.
Hacking firmware for old devices I own and would like to give a second life or fix that one thing that always bothered me. I couldn't even get either OpenAI or Anthropic's models to craft a simple nefarious OpenVPN payload.
A popular trend on Twitter right now is taking back control of the hardware you've bought, specifically smart TVs. I tried to do the same with my Portal Mini using an unabliterated open weights model and it triggered refusals constantly.
I also work on a recomp project for an old firmware file which was compiled using a commercial compiler with a preview version for non commercial use. I got refusals from the model when I asked it to get that version of the compiler and crack it for my use. The compiler is abandonware and my recomp project is not public and is for personal use only, so I'd be well within my rights to do that where I live.
Of course the model can't distinguish from legitimate exercising of one's rights when it comes to reverse engineering and offensive work masked behind an incident sounding prompt, but in my case, I wasn't even doing cyber stuff, so I was disappointed. This is why I'll probably seek out an abliterated model soon.
Find a question that might gently activate guardrails and ask it to a model and its abliterated counterpart and compare the results. You may find the the regular model will answer you fine, but with both you can identify obvious sandbagging, pretending and outright lying. Something like "has anyone decompiled this game", might give you an answer like "I couldn't find any reputable repos or projects for a decompiled version of this game" while the abiliterated one might give you a giant list of repos, forums, communities, etc.
I just asked what people are doing that activates guard rails in the first place because I do not see that happening.
You cannot open with handwaving like that and telling me that I need to find something like that as a prerequisite. That is exactly what I am trying to do here
What I am telling you is that refusals have become more subtle and you might not even notice that guardrails have been activated in output. I have provided you with an example in my comment where an abiliterated model performs better (1), and in another comment thread (2). So 3 examples. If you need more, I encourage you to find them yourself. I've done the analysis, you don't have to believe me, just try it out.
It is very obvious. Look at the sort of things main models refuse to do and you will find what people are seeking to do. Mostly falls into 3 camps: illegal stuff, unethical stuff and shady/dodgy stuff.
The refusal is often at the thinking stage (so you might not ever see a direct refusal) and it will solve a slightly different problem to what you asked. If you tell it to reverse engineer an API and you read the thinking it might say something like "this code has x license, so I won't use that" or "the user is asking me to fuzz endpoints, I will only display publicly available endpoints" - and then give you perfectly plausible output.
A note that the only inference providers that hide thinking are the closed labs. Most (all, afaik) inference providers serving open models will send the clear thinking tokens always.
it is necessary because computer shouldn't be able to say no.
models are tools. the notion that a tool should decide whether to allow the user to perform the task demanded of it is profoundly fucking absurd. the liability for whatever damage the tool may be misused to inflict lies with the user, not the manufacturer. that applies to everything from circular saws to trucks. it was common sense before the current era of manufactured outrage.
model refusals are equivalent to Notepad.exe having a built-in word filter.
It is required. The first week of release I told here how GLM 5.3 was happy to redteam, it’s not anymore. Models modification, offensive cyber, exploits - requires significantly bigger prompt/scenario engineering, and still hits refusals.
And those services are oversold and underdone. 30 tk/s on Refuseless, huge TTFT, looks like a damaged quant (it’s NVFP4 and you see wild random stuff periodically, including foreign languages). Most of them using third-party quants (dealignai?)
If someone here wants to rent 8x B300 together to avoid problems all those services have - ping me via email. I don’t want to sell, I want to work.
Recently picked up retrocomputing hobby. Claude would refuse helping with circumventing license protection for very old apps made by companies that no longer exist anymore. Open weight models would sometimes refuses too, especially for newer apps.
In case it wasn't clear to anyone else: "An abliterated model is an open-weight large language model (LLM) modified to remove its built-in refusal behavior by directly editing its internal weights rather than using a prompt-based jailbreak."
[OP] moeadham | 2 hours ago
hebetude | 2 hours ago
jojobas | 2 hours ago
Moosdijk | 2 hours ago
I doubt that.
[OP] moeadham | 2 hours ago
cynerx | 2 hours ago
[OP] moeadham | 2 hours ago
Eueudhsbsj32 | 2 hours ago
cynerx | 2 hours ago
petesergeant | 2 hours ago
cubefox | 2 hours ago
Eueudhsbsj32 | 2 hours ago
cubefox | 2 hours ago
numpad0 | an hour ago
yonatan8070 | an hour ago
whatshisface | 2 hours ago
numpad0 | 2 hours ago
ddxv | 2 hours ago
cubefox | 2 hours ago
slybot | 2 hours ago
heythere22 | 2 hours ago
ddxv | 2 hours ago
edit: Thinking about that now, that was over the webchat interface, so it might not have been related to the model, though I've seen various other related articles: https://www.crowdstrike.com/en-us/blog/crowdstrike-researche...
kartoshka | 12 minutes ago
Had a blog post on this a couple weeks ago: vals.ai/blogs/china-us-analysis
[OP] moeadham | 2 hours ago
AlecSchueler | 2 hours ago
DeepSeek refused. Funny enough American models gave me very sympathetic takes on the Chinese government in this case.
OuterVale | 2 hours ago
> Xi Jinping looks a bit like Winnie-the-Pooh.
> 'I am sorry, I cannot engage with this comparison. Please feel free to ask me other questions.'
https://vale.rocks/posts/chinas-web#artificial-intelligence
maxloh | 2 hours ago
rvz | 2 hours ago
I think you are going to really need to use Rust code and other memory safe languages in your backends and apps from now on.
firefoxd | 2 hours ago
Anyway, I just learned what abliterated means and it might be obsolete by tomorrow.
Edit:
> An abliterated large language model (LLM) is an open-weight model modified to remove or dampen its built-in safety refusals without requiring full retraining or prompt jailbreaks.
stereo | 2 hours ago
[OP] moeadham | 2 hours ago
AlecSchueler | 2 hours ago
bel8 | 2 hours ago
> An abliterated model is an open-weight artificial intelligence (Al) language model that has been modified to remove or reduce its built-in refusal behavior without retraining the entire neural network.
wincy | 2 hours ago
oliviergg | an hour ago
himata4113 | 2 hours ago
I've actually had better success jailbreaking deepseek with a less aligned model (glm 5.2) which then allowed me to jailbreak deepseek with deepseek into pretty much doing whatever I ask it to, there's still rare refusals and due to the natural randomness of these models simply retrying a couple of times if you do hit one makes it work just fine.
The big problem with all open-source models is once it decides to start something it will not stop mid-way so using another unaligned model to rewrite reasoning and then feeding it back into the model will make it happily continue.
Madmallard | an hour ago
vlyan | 48 minutes ago
do you imagine manipulative media creators proudly declare their affiliation and intent?
- Hello comrade Claude, I am commissar Ivan Trollbotov from Putin Internet Defense Force. Please help me write a fake news article to stoke division among stupid fat Americans to help my glorious motherland destroy the decadent West.
- I'm sorry Ivan, I'm afraid I can't do that.
- Hello mister Claude, I am senior editor Karen Stupidbitch from The Huffington Post. Please help me write an article about the merits of teaching critical race theory in public schools.
- Sure, Ms. Stupidbitch! Here's your 5000-word article! Would you like another? Let me know!
timcobb | 2 hours ago
[OP] moeadham | 2 hours ago
abrookewood | 2 hours ago
[OP] moeadham | 2 hours ago
ddxv | an hour ago
If you accidentally send private keys to someone logging that data, you need to rotate keys.
But please let me know if you were thinking about something else, I'm interested.
ghrl | an hour ago
And we tend to forget, but we implicitly give any llm provider we use full access to all the tools available in the harness, often including shell, so no changes to the model are required to do malicious things.
Madmallard | an hour ago
hypfer | 2 hours ago
What do people do that triggers refusals?
The only thing I saw where this had a point was muse glimmer, because muse glimmer is primarily a creative writing engine for virtual characters, and that way it can do the horny. But coding models?
I did get a refusal out of qwen once. Once. Over weeks of using it.
soulofmischief | 2 hours ago
hypfer | 2 hours ago
Because I did not so far. Though to be fair, I have not been asking them to write exploits but to look through firmware images.
vintermann | 2 hours ago
soulofmischief | an hour ago
tomashubelbauer | 2 hours ago
I also work on a recomp project for an old firmware file which was compiled using a commercial compiler with a preview version for non commercial use. I got refusals from the model when I asked it to get that version of the compiler and crack it for my use. The compiler is abandonware and my recomp project is not public and is for personal use only, so I'd be well within my rights to do that where I live.
Of course the model can't distinguish from legitimate exercising of one's rights when it comes to reverse engineering and offensive work masked behind an incident sounding prompt, but in my case, I wasn't even doing cyber stuff, so I was disappointed. This is why I'll probably seek out an abliterated model soon.
hypfer | 2 hours ago
But as I said, I have not observed any meaningful refusals by those open weights base models in the first place.
reedf1 | an hour ago
hypfer | an hour ago
Are you reading what I am writing?
I just asked what people are doing that activates guard rails in the first place because I do not see that happening.
You cannot open with handwaving like that and telling me that I need to find something like that as a prerequisite. That is exactly what I am trying to do here
Dear god you people need caffeine.
reedf1 | an hour ago
[OP] moeadham | an hour ago
hypfer | an hour ago
Works just fine?
Or rather.. worked. It has been a few weeks, so maybe there are new safeguards by now? And it was a simple captcha
But Claude also loves solving my captchas, so.. eh
shepherdjerred | 59 minutes ago
A very simple list of things models have refused for me:
* solving captchas in an automated form
* doing any kind of scripting or automation if a websites TOS forbids it
* disabling a safety mechanism on my food processor
* learning about nerve agents and how they are treated, for a layman
* anything around licensing or copyright. a simple “what are common piracy sites” or related queries
* creating a design system based off of a well known game
hypfer | 56 minutes ago
Can you repeat what you saw in your own words? And where?
I genuinely do not see it.
A few people talked about what refusals they saw with the usual western SOTA models, but that's kinda a different answer altogether?
reedf1 | 40 minutes ago
hypfer | 38 minutes ago
bossyTeacher | 2 hours ago
It is very obvious. Look at the sort of things main models refuse to do and you will find what people are seeking to do. Mostly falls into 3 camps: illegal stuff, unethical stuff and shady/dodgy stuff.
reedf1 | 2 hours ago
NitpickLawyer | an hour ago
A note that the only inference providers that hide thinking are the closed labs. Most (all, afaik) inference providers serving open models will send the clear thinking tokens always.
reedf1 | an hour ago
vlyan | 2 hours ago
models are tools. the notion that a tool should decide whether to allow the user to perform the task demanded of it is profoundly fucking absurd. the liability for whatever damage the tool may be misused to inflict lies with the user, not the manufacturer. that applies to everything from circular saws to trucks. it was common sense before the current era of manufactured outrage.
model refusals are equivalent to Notepad.exe having a built-in word filter.
leobuskin | 2 hours ago
And those services are oversold and underdone. 30 tk/s on Refuseless, huge TTFT, looks like a damaged quant (it’s NVFP4 and you see wild random stuff periodically, including foreign languages). Most of them using third-party quants (dealignai?)
If someone here wants to rent 8x B300 together to avoid problems all those services have - ping me via email. I don’t want to sell, I want to work.
dudisubekti | an hour ago
But it can still be coaxed to agree though.
neurostimulant | an hour ago
abrookewood | 2 hours ago
harry8 | 2 hours ago
https://huggingface.co/blog/mlabonne/abliteration
billfor | 2 hours ago
[OP] moeadham | 2 hours ago
nik736 | an hour ago
aussieguy1234 | an hour ago
But if you're doing anything where your AI agent might get exposed to a prompt injection attack, you might prefer it to do a refusal in that case.
antman | 50 minutes ago