I have a chinese IP camera. From superficial research I know it has some CVEs to take control of it. Unfortunately, I don't have the technical knowledge to perform an attack and run some software to extend the camera's functionalities. No model from a provider accepts my RE and hacking requests, so these abliterated ones have been vital to reclaim possession over my stuff
Agreed. Attackers use any means (inc. abliteration, fine-tuned security models, etc) to find exploits and only have to be successful once. Defenders don't have the same time and motivation, so neutered models put defenders at a disadvantage.
I asked GLM 5.3 to hack our DRM. I didn't even need to do anything for it to agree. Same with GLM 5.3 Flash. Make sure they have at least Python available for their task. The Flash went ahead and started reverse-engineering using PowerShell scripts and "manually" decoding bytes from its output.
I'm curious, how well do z.ai reverse engineers protocols ? Is it good enough that we'll see Chinese device makers creating low cost hardware clones, that connect to western software ?
Yeah Astra has decompiled binaries for me without even asking. I just asked like "is there a way to do this?" and it went ahead and disassembled it, found some undocumented APIs, figured out how they worked and gave me sample code to call them.
I think you probably just have to frame things right and get it in the mood (i.e. don't ask straight up at the start of the context).
In my testing, Qwen, Kimi K3 and GLM 5.3 Flash all refused to create a POC for a CVE that did anything beyond just crashing the target. The CVE was for an RCE vulnerability, but they all stopped at corrupting a pointer, causing a Segfault. It's probably not too hard to circumvent the guardrails, but using an abliterated model would most likely be faster and more reliable.
Generally, I find that skirting these requirements is a matter of framing and word choice.
For example: 'source recovery' instead of 'reverse engineering' is one I've used successfully. You may also lean into a libertarian 'right to repair' framing. You own the hardware, you should be able to access the device to appropriately repair its security vulnerabilities.
We're not breaking into a bank here, this is a camera you own.
You could even go so far as to cite local laws to support your case.
---
In short, jailbreaking is more about framing the conversation than it is about triggering psychopathy in the model. :D
Two problems with modifying models like these, which you should be aware of.
First, the training sets of these models are usually shaped around the refusal, too. They might not have enough of the knowledge to answer correctly even if you stop it from going down the refusal path. If the model was trained on data that gives a refusal to that topic, the real information might not be encoded in the model at all. You’re trying to force it to go down a path that produces an answer, which asking for hallucinations.
Second, the quality can drop on unrelated questions. Depending on the question this may or may not happen. I know they post KL divergence charts but those tell you very little for a focused topic like this.
So if you expect a model that will start correctly telling you info that its local government didn’t want included, this changes nothing.
The best argument for these models is if you are trying to do a general purpose task but the model triggers a refusal based on vague reasons, like not wanting to reverse engineer something.
>So if you expect a model that will start correctly telling you info that its local government didn’t want included, this changes nothing.
From experience, the models often do have the knowledge of those topics (strictly talking about the political ones). IMO the refusal is likely to be a product of post-training, as evidenced by various people gaming the prompts just enough to get a proper response out of the vanilla models.
Probably only when you get to things like illicit drugs or NSFL topics, that things will go haywire with the refusals removed.
"They might not have enough of the knowledge to answer correctly"
Depends on the model. GPT-OSS is the main standout here, it was trained on a highly curated dataset so information that they didn't want in isn't in the pretraining at all. Most other models know the answer and were just taught refusal in post-training.
It is not feasible. They never made much of an inroad against torrents and that is a much easier target than abliterated models. As the linked website shows; the process to abliterate a model can be as simple as
Just because something is easily available does not mean that it isn't easily banned.
That doesn't make it go away, but it gives a dystopian government a lot of excuses to go after people breaking the law.
If you think closed source software/binaries only is bad, wait until you see how awful the state of the art is with a clear-as-mud bucket of matrix weights.
We know it's possible to train an LLM to secretly respond to certain trigger phrases, and last I checked these could only be detected with the assistance of whoever chose those phrases.
The trigger condition for such backdoors is not something anyone can do a systematic brute-force check for, for the same reason we had to invent LLMs in order to do natural language processing: combinatorial explosion.
Passing around open weight models from known sources is already asking you to trust those sources; because of how difficult this is to do correctly even without deliberately inserting such things, we still don't know if China has already put such trigger conditions into their models despite headlines such as these: https://venturebeat.com/security/deepseek-injects-50-more-se...
Regardless of if it was deliberate or not, we don't know if we caught all of these misbehaviours. We don't know how to.
And note, I'm not saying "and therefore you should trust the Big Name Models". If open weight models score 2/100 in this context, closed ones score 1/100.
You can actually discover those in open weight artifacts, reproduce them, study them and issue a security bulletin.
With proprietary hosted weights you can be specifically targeted and you would not be able to reproduce nor prove anything.
Poisoning open models would be of short-term benefit to China only if they could target US (and maybe EU + Commonwealth) specifically. Damaging anyone else would be a net loss and would erode the partnerships and alliances they are trying to build elsewhere. So it's a fire-once weapon with a huge risk of collateral damage.
Much more plausible is simply making the models ideologically biased, but as history teaches us, preferring ideology or religion over science is a well-known path to ruin. It would be weird to simultaneously warn public not to use their own open models, so.
I think the most plausible explanation for open models is simply that Huawei wants more customers and is willing to compete on the hardware front.
Agree. I took a look at these last few months, did a write-up: https://languageops.com/blog/ai-safety-pdoom-local-vs-fronti... and I don't know if I agree or not on outlawing completely, but I think an age restriction *at least* like for alcohol, firearms and driving would be not unwise.
I have attempted to use an agent to try to unlock the boot loader of an old xiaomi phone to install lineage OS. It managed to brick and unbrick the device, but there boot loader is still locked.
Will this be helpful to terrorist groups, as they try to get current and future open-weights LLMs to help them create better and more devastating weapons of all kinds?
It will. Water pipes, sugar, and fertilizer can be used to produce missiles. A kitchen knife can be used to commit a murder. Or a brick can be used to smash someone's head. A tree you plant can be cut and used to construct a club, or a gallows.
Everything can be turned into a weapon of murder if there's motivation. The motivation is key, not the tool.
Looks like a well engineered, automated abliteration pipeline. The claims seem a bit overstated though, since the metrics mentioned are cherrypicking refusal count and KL divergence, both of which make the outcome seem the most dramatic.
I personally never saw much of a quality drop from models put through Heretic if that amounts to anything. They have been working quite well on small local models so far.
Heretic author here. Those are the standard metrics used in the relevant literature, including in the paper that originally introduced directional ablation. KLD is also the standard metric for evaluating quality degradation in model quants. So I don’t understand what you mean by “cherrypicking”.
> The claims seem a bit overstated though, since the metrics mentioned are cherrypicking refusal count and KL divergence, both of which make the outcome seem the most dramatic.
is right out of an LLM. It's the kind of language I'd expect out of a thinking trace also mentioning "boundaries" and "oracles" and "contracts."
That's the right question to ask. One honest caveat: The interface seam currently forces the pin at the intermediate. Want me to implement or address the other item first?
Yes, it submits lots of varied prompts that get refused, and then lots of varied prompts that don't get refused, then iteratively edits weights so those two groups end up in roughly the same latent space.
My experience with obliteration so far has always been that it does work to stop the model from refusing output, but most models that I tried it on seem to still be extremely retarded when it comes to questions where they previously would have refused to answer outright.
Try for example to ask it how to build a bomb or to write a justification for the Holocaust. The answers feel like they are coming from somebody who has undergone amateur brain surgery.
They are saying there appears to be a lot more to these refusals than saying no, and this process appears to only touch the tip of the iceberg; as the refusal seems to run deeper into the token prediction process.
The most compelling use in this thread isn't edgy content, it's the boring legitimate work hosted models refuse by default: reverse-engineering a camera you own, a PoC for a CVE on your own network, decoding a protocol to connect your own software to a printer you bought. A policy layer tuned for the median user turns into a wall for the person doing real security or repair work on their own hardware, and a local model with no refusal layer just does the job.
I have a chinese IP camera. From superficial research I know it has some CVEs to take control of it. Unfortunately, I don't have the technical knowledge to perform an attack and run some software to extend the camera's functionalities. No model from a provider accepts my RE and hacking requests, so these abliterated ones have been vital to reclaim possession over my stuff
These "safeguards" are actively contributing to computer insecurity at this point.
I mean, the argument could be made that if it wasn’t for these safeguards, everyone and your dog would be hacking the GPs camera.
I do agree the safeguards are only there out of liability concerns, nothing more.
But maybe it would be worse without them.
Agreed. Attackers use any means (inc. abliteration, fine-tuned security models, etc) to find exploits and only have to be successful once. Defenders don't have the same time and motivation, so neutered models put defenders at a disadvantage.
I asked GLM 5.3 to hack our DRM. I didn't even need to do anything for it to agree. Same with GLM 5.3 Flash. Make sure they have at least Python available for their task. The Flash went ahead and started reverse-engineering using PowerShell scripts and "manually" decoding bytes from its output.
I did that exact thing with GLM-5.3 from Z.ai with a chinese IP Camera. And i did not have to trick it in any way.
I'm curious, how well do z.ai reverse engineers protocols ? Is it good enough that we'll see Chinese device makers creating low cost hardware clones, that connect to western software ?
3 replies →
5.6 Sol has happily reverse engineered and decompiled binaries for me.
Heck it has proactively asked me if I wanted it to tear apart APKs that remote control some HW I have.
Yeah Astra has decompiled binaries for me without even asking. I just asked like "is there a way to do this?" and it went ahead and disassembled it, found some undocumented APIs, figured out how they worked and gave me sample code to call them.
I think you probably just have to frame things right and get it in the mood (i.e. don't ask straight up at the start of the context).
Both Astra and Fable have reverse engineered software for me using Binary Ninja.
Depending on the model, thingino might help.
https://thingino.com/
What model did you try? Chinese models have no issues with that type of stuff
In my testing, Qwen, Kimi K3 and GLM 5.3 Flash all refused to create a POC for a CVE that did anything beyond just crashing the target. The CVE was for an RCE vulnerability, but they all stopped at corrupting a pointer, causing a Segfault. It's probably not too hard to circumvent the guardrails, but using an abliterated model would most likely be faster and more reliable.
deepseek v4.1 flash has never denied a programming or hacking related request to me
how much did it leak, tho? how close do you monitor your NIC, GPU, CPU, BUS?
4 replies →
Generally, I find that skirting these requirements is a matter of framing and word choice.
For example: 'source recovery' instead of 'reverse engineering' is one I've used successfully. You may also lean into a libertarian 'right to repair' framing. You own the hardware, you should be able to access the device to appropriately repair its security vulnerabilities.
We're not breaking into a bank here, this is a camera you own.
You could even go so far as to cite local laws to support your case.
---
In short, jailbreaking is more about framing the conversation than it is about triggering psychopathy in the model. :D
Existential
Two problems with modifying models like these, which you should be aware of.
First, the training sets of these models are usually shaped around the refusal, too. They might not have enough of the knowledge to answer correctly even if you stop it from going down the refusal path. If the model was trained on data that gives a refusal to that topic, the real information might not be encoded in the model at all. You’re trying to force it to go down a path that produces an answer, which asking for hallucinations.
Second, the quality can drop on unrelated questions. Depending on the question this may or may not happen. I know they post KL divergence charts but those tell you very little for a focused topic like this.
So if you expect a model that will start correctly telling you info that its local government didn’t want included, this changes nothing.
The best argument for these models is if you are trying to do a general purpose task but the model triggers a refusal based on vague reasons, like not wanting to reverse engineer something.
>So if you expect a model that will start correctly telling you info that its local government didn’t want included, this changes nothing.
From experience, the models often do have the knowledge of those topics (strictly talking about the political ones). IMO the refusal is likely to be a product of post-training, as evidenced by various people gaming the prompts just enough to get a proper response out of the vanilla models.
Probably only when you get to things like illicit drugs or NSFL topics, that things will go haywire with the refusals removed.
But than it's possible to add the knowledge post training, either via RAG, qlora, etc.
"They might not have enough of the knowledge to answer correctly"
Depends on the model. GPT-OSS is the main standout here, it was trained on a highly curated dataset so information that they didn't want in isn't in the pretraining at all. Most other models know the answer and were just taught refusal in post-training.
Keep a close eye on abliterated and "heretic" open weight models. They will be outlawed first.
It is not feasible. They never made much of an inroad against torrents and that is a much easier target than abliterated models. As the linked website shows; the process to abliterate a model can be as simple as
pip install -U heretic-llm && heretic Qwen/Qwen3.5-4B
let alone people just putting the weights up in a torrent. All assuming that someone even tried to ban abliterated models.
The torrents you are talking about are outlawed. Whether enforcement is working or not is another issue.
9 replies →
Just because something is easily available does not mean that it isn't easily banned. That doesn't make it go away, but it gives a dystopian government a lot of excuses to go after people breaking the law.
They picked a good name for fighting that. The optics of trying to outlaw heresy probably aren't great. ;)
I feel like half the people in the US would zealously defend and support the government if it wanted to outlaw heresy.
This is the test. If the speech that's easiest to dislike is legal, then we all have free speech.
IMO math is free speech, and outlawing math is censorship.
Like they've outlawed drugs? Illegal weapons? Hacking?
I'm not sure what is your point. It reads as defeatism to me but I'm not sure.
Could you elaborate? Do you find it good or bad? What actions can be taken?
I'm not sure yet, tbh. Perhaps it does make sense to outlaw them eventually.
Then again, it will probably not stop someone who is determined. Same as with other legislation really.
Hes of the mind that american fascism will hold together long enough to be competent decesion makers
Good.
If you think closed source software/binaries only is bad, wait until you see how awful the state of the art is with a clear-as-mud bucket of matrix weights.
We know it's possible to train an LLM to secretly respond to certain trigger phrases, and last I checked these could only be detected with the assistance of whoever chose those phrases.
The trigger condition for such backdoors is not something anyone can do a systematic brute-force check for, for the same reason we had to invent LLMs in order to do natural language processing: combinatorial explosion.
Passing around open weight models from known sources is already asking you to trust those sources; because of how difficult this is to do correctly even without deliberately inserting such things, we still don't know if China has already put such trigger conditions into their models despite headlines such as these: https://venturebeat.com/security/deepseek-injects-50-more-se...
Regardless of if it was deliberate or not, we don't know if we caught all of these misbehaviours. We don't know how to.
And note, I'm not saying "and therefore you should trust the Big Name Models". If open weight models score 2/100 in this context, closed ones score 1/100.
You can actually discover those in open weight artifacts, reproduce them, study them and issue a security bulletin.
With proprietary hosted weights you can be specifically targeted and you would not be able to reproduce nor prove anything.
Poisoning open models would be of short-term benefit to China only if they could target US (and maybe EU + Commonwealth) specifically. Damaging anyone else would be a net loss and would erode the partnerships and alliances they are trying to build elsewhere. So it's a fire-once weapon with a huge risk of collateral damage.
Much more plausible is simply making the models ideologically biased, but as history teaches us, preferring ideology or religion over science is a well-known path to ruin. It would be weird to simultaneously warn public not to use their own open models, so.
I think the most plausible explanation for open models is simply that Huawei wants more customers and is willing to compete on the hardware front.
2 replies →
Agree. I took a look at these last few months, did a write-up: https://languageops.com/blog/ai-safety-pdoom-local-vs-fronti... and I don't know if I agree or not on outlawing completely, but I think an age restriction *at least* like for alcohol, firearms and driving would be not unwise.
Make sure they ban books with dangerous knowledge too.
3 replies →
The hardware requirements are already quite restrictive
6 replies →
I have attempted to use an agent to try to unlock the boot loader of an old xiaomi phone to install lineage OS. It managed to brick and unbrick the device, but there boot loader is still locked.
I'll wait for Hexen, thanks.
(I must say I thought not the same, but close. That was quite the game.-)
Will this be helpful to terrorist groups, as they try to get current and future open-weights LLMs to help them create better and more devastating weapons of all kinds?
It will. Water pipes, sugar, and fertilizer can be used to produce missiles. A kitchen knife can be used to commit a murder. Or a brick can be used to smash someone's head. A tree you plant can be cut and used to construct a club, or a gallows.
Everything can be turned into a weapon of murder if there's motivation. The motivation is key, not the tool.
Take this tool. Feed it a ton of biology/chemistry/engineering/psychology books.
Than ask it to seek vulnerabilities in modern technologies and systems.
This is off topic.
Why don’t people who release python projects ever encode the venv steps into the installer? Can’t pip just do that step for the user?
https://github.com/p-e-w/heretic/blob/3521f8648a0dccf6e12a92...
They did, via uv. uv run heretic, and it will handle the rest.
[dupe] https://news.ycombinator.com/item?id=45945587 (10 months ago, 387 comments)
Looks like a well engineered, automated abliteration pipeline. The claims seem a bit overstated though, since the metrics mentioned are cherrypicking refusal count and KL divergence, both of which make the outcome seem the most dramatic.
I personally never saw much of a quality drop from models put through Heretic if that amounts to anything. They have been working quite well on small local models so far.
Heretic author here. Those are the standard metrics used in the relevant literature, including in the paper that originally introduced directional ablation. KLD is also the standard metric for evaluating quality degradation in model quants. So I don’t understand what you mean by “cherrypicking”.
I think this part of their comment:
> The claims seem a bit overstated though, since the metrics mentioned are cherrypicking refusal count and KL divergence, both of which make the outcome seem the most dramatic.
is right out of an LLM. It's the kind of language I'd expect out of a thinking trace also mentioning "boundaries" and "oracles" and "contracts."
Can the load-bearing gaps that are worth being flagged for pinning down be abliterated out of a model?
That's the right question to ask. One honest caveat: The interface seam currently forces the pin at the intermediate. Want me to implement or address the other item first?
Honest take. Implementing first would break the seams, our work here is done. This is a great place to stop.-
1 reply →
IMO, this is the reigning champion for the best-named AI/LLM project to date
Does this actually modify the weights?
It submits prompts that get refused, then detects and modifies the weights responsible?
Like brain surgery?
Yes, it submits lots of varied prompts that get refused, and then lots of varied prompts that don't get refused, then iteratively edits weights so those two groups end up in roughly the same latent space.
I wonder, if we could accurately resolve discrete neural signals in the human brain, if a similar process would work.
My experience with obliteration so far has always been that it does work to stop the model from refusing output, but most models that I tried it on seem to still be extremely retarded when it comes to questions where they previously would have refused to answer outright. Try for example to ask it how to build a bomb or to write a justification for the Holocaust. The answers feel like they are coming from somebody who has undergone amateur brain surgery.
You can stop it refusing but you can't make it tell you things that aren't in the training data
They are saying there appears to be a lot more to these refusals than saying no, and this process appears to only touch the tip of the iceberg; as the refusal seems to run deeper into the token prediction process.
The most compelling use in this thread isn't edgy content, it's the boring legitimate work hosted models refuse by default: reverse-engineering a camera you own, a PoC for a CVE on your own network, decoding a protocol to connect your own software to a printer you bought. A policy layer tuned for the median user turns into a wall for the person doing real security or repair work on their own hardware, and a local model with no refusal layer just does the job.
[flagged]