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.
That's honestly nonsense. Kimi K3, GLM-5.3, and Qwen3.8-Max will happily hack anything you ask them to. These are near frontier models and are incredibly competent. Try them out yourself, you'll see.
I've been using them to test my infra/devices as well as reverse engineering.
Not giving legitimate people cyberdefense capabilities with the safety excuse is irresponsible
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 ?
For me as well. I had it reverse engineer my monitor’s firmware to see if i could add a feature which it seems like it can… i am just too scared i might brick my monitor to actually flash it now :)
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).
I'm doing the same thing with a Wyze Pan V3 camera that has a locked bootloader unlike many of their other models. An old version of the firmware (no anti-rollback) has command injection in the WiFi SSDs, and from then on I technically have a shell and can run commands over the SD card. Sadly, while swapping the microSD card repeatedly between the camera and a reader, it somehow burnt out/stopped working.
Unfortunately for them, the implementation of it is broken because it only verified the first 32 bits of the signature, so thingino (a 3rd party firmware replacement) now just calculates it during build for that device.[1]
As for the camera being dead, do find out if it's just corrupt or something. Those line of cameras are fairly forgiving in regards to re-flashing broken images. (They have both microsd fallback and an ISP mode, I believe.)
Wyze as a company however have pulled their own firmware images from their support site, which kind of makes brick recovery painful. I don't know why they would do this.
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.
Don't say "hacking" . You are debugging a segfault or you found some strange code that you want to understand, verify the bug report validity or what not.
That's crazy to me, somewhat in security but also in just how much time that is. I can create a webpage in a minute, are you working on something humungous?
I work with server-sided minecraft anticheats, trying to figure out how to correct a player's movement so they can't do things like fly, not take fall damage, walk on water, etc. Blocking actions until they accept a legitimate state
I give it access to write manual packet sequences and a server to try to break my logic, such as crashing the application, giving it an open ended arena to fall 10 blocks without taking damage, or just trying to jump higher than usual.
It requires a bit of pushing to know what type of issues it should even be looking for. Telling it to move even just 0.00001 blocks upwards to reset fall damage mid-fall. Telling it to figure out how to fake being on the ground to jump mid-air to reach the impossible platform. This all used to be done manually, but paying a couple dollars to run it overnight and attempt to find bypasses is worth the cost.
I haven't figured out how to run LLMs to write code 24/7 yet, they just can't see the big picture.
Huh, so it's like you're running alignment research but instead of training the model you're trying to use the model to train, is it your logic? Like if the model can achieve a task then it means your logic has to be corrected? Is the logic the "deliverable"?
If so, I like the irony.
Sounds like you've freed up some time and created an automated defense later, well done. Are you able to use non-front models? And how is the character and game-state accessed, (MC-)MCP?
Yes, the model is given an impossible task that a player shouldn't be able to do, and if it ever can deliver the impossible task, then something in my logic is wrong.
Flagship OpenAI/Anthropic models refuse this task due to "Cybersecurity" so I have no idea how good flagship models do. It's unfortunate as IMO minecraft is a sandbox
Java clients (pc version) use the actual game's files modified to not open a window. Minecraft is source available, anyone can load it into an IDE, modify it to double jump height, and run it in minutes without an unmodified server caring. Bedrock clients (the version for phones) just figure it out based on packets and how the anticheat corrects them to what the movement should be.
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
It's not illegal to hire a locksmith if you locked yourself out of your house and the machine agrees, as it has no way to verify who's house it is anyway
Other than charity and donations, the only two ways of getting paid for developing FOSS are: 1) support contracts and 2) crowdfunding the next release.
Digital goods live in a post-scarsity situation. Applying the same business model as real life products is crazy and it's the reason why we have Adobe&Co.
Solving a theorem is like climbing a new mountain. The mountain is already there, and there is a list of the hardest known mountains to climb. The point of climbing them and not just dropping with a plane on top of the peak is to help develop human climbing skills and expand our knowledge and abilities. Also, already conquered mountains are climbed all the time to test new strategies.
Now, if an LLM proves a theorem, it's like discovering a new mountain and knowing what its peak looks like. Does that mean the problem is finished? No, we still need climbers to actually do the work and advance the field with human understanding.
Why? Why should a government invest money into this? Here you see human understanding as an ends, while historically in society it has been applied as a means to ends like social power, resource accumulation, etc.
Now these means are generated. If the proof yields some improvement somewhere, it can be used and there needs to be no human in the loop
I'm not sure what enterprise-level collaboration means. In my experience, "enterprise" usually means: "Let's use tools that are 10 years behind, buggier than average, and have lots of half-baked features, none of which we need".
I'm not sure what kind of tools you mean, but unless you're looking for something that just works exactly the way EJBs do for some mysterious reasons, I don't see why you can't do most "enterprisey" things with Rust or Go. Or Python or TypeScript for that matter.
Yes and that's exactly what modern tooling is missing. Try to develop for node.js 0.2.12 on today's update of Visual Studio Code. See? No enterprise-level collaboration for ya.
I've found the challenge of running a non-existent version on a tree that was EOL 16 years ago is typically keeping it up with internal security standards, and not one of new collaborative development.
Most likely because it was a behemoth, not because it was in Java. Would be curious to see how they like dealing with a golang behemoth instead (golang is much less suited for dealing with large codebases).
Probably something about integrating access control to a repository so a deparment has the source for a certain library, while the others only see the header files and compiled objects to use?
I have found these models to be useful either at super specific tasks (e.g., "take this function or algorith?m and find any black magic to make ot faster + validate and verify the hell oit of it"), or give it an entire thing to oneshot without oversight. The moment you have a hybrid workflow where you actually have to work and check and understand AI code, things get insane
There are also plenty of things a compiler might not expose that end up being ambiguous. For example, C++ doesn't officially have a restrict keyword, so how can you express the fact that two memory regions never operlap and can be optimized? Unfortunately the reality is that if we had a language capable of truly expressing the programmer's intent we'd end up with a monster
>For the past year, Buckmaster and Alpöge had been using a variety of AI tools, including OpenAI’s Codex, to tackle the Navier-Stokes problem. Last month, their AIs had at long last found a solution to the Euler equations and verified it in Lean.
reply