Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

xda-developers.com

Post reply on HN
Print view View original

81–90 of 161 posts

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#81

Post by mdp2021 »

> As it turns out, probably unsurprisingly, Qwen recognizes common jailbreak attempts, and one of the first things it told me was that it wasn't going to fall for the jailbreak prompt

Now also see latest submission, https://news.ycombinator.com/item?id=49409073 :

# I spent $266 and four AI models to own my tablet. GLM-5.3 finished it in a day

> Quick context: the tablet is a 2021 Fire HD 10 that ran my Home Assistant dashboard and kept powering itself off: the logs showed Amazon's own software issuing the shutdowns, and the only permanent fix was root, which has never existed publicly for this model. Anthropic's and OpenAI's cyber safeguards wouldn't touch the project

Why should Anthropic and OpenAI thrive: they do not work on real problems.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#82

Post by colingauvin »

Neywiny wrote: post #43
pi-victor wrote: post #20

i'm not good with paper work, in fact, i'm horrible with anything that's paperwork related. for the past few days, i ran this model on my rtx 4090 + rtx 3070 and told it to check all the bills, invoices, contracts for me and my small company. i used pi with llama and the pi-llama plugin. oh, boy - i hooked it to my email, told it to download all of the invoices and bills i had for both me and my company and organize…

Pro tip: usually you can download your emails to an offline collection. That way there's no risk. Hooking it up to your email sounds very very risky.

You can also just do read only access through most mcp servers for functionally no difference

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#83

Post by xyzzy123 »

addaon wrote: post #78
xyzzy123 wrote: post #54

Earlier quoted context omitted.

I don't fully understand the instinct to regulate local models for this? It seems like the wrong place to address the problem. You can download Ebola sequences right now if you want to. That's not the same as having an isolate. The difference is a lot of messy reality. This kind of work is not generally "one shot" (Claude make me a supervirus, make no mistakes), it requires lab space, iteration, and specific resource…

It depends how easy it is (now, or in the near future) to turn information into weapons, and how realistic control of materials is. There's a reason we control access to plutonium, but information about metastable hafnium.

It does seem to me that for this specific problem the materials are a lot more amenable to control than the information is?

There's also this weird revealed threat model thing going on? Like why does it make sense to support heavy LLM restrictions but leave benchtop oligo synthesisers completely unregulated? (Note: I do agree that wanting to regulate BOTH is at least a consistent and defensible position).

I find it philosophically interesting because the problem is not strictly information control. Local models don't have any special extra information with respect to biological research. What has to be restricted is using information that's already publicly known in the wrong ways.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#84

Post by TofuLover »

Xunjin wrote: post #63
TofuLover wrote: post #50

Earlier quoted context omitted.

More seriously though, I think we should be fine: we don't host any content, and what people do with the models is their own responsibility (legally speaking, in our jurisdiction, at least according to Claude -- we're talking to a real lawyer next week). Like any other provider, we offer no guarantees of sane, safe, or accurate results.

>legally speaking, in our jurisdiction, at least according to Claude -- we're talking to a real lawyer next week That's going to be fun lol

We look forward to providing many headaches to our lawyers going forward.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#85

Post by jszymborski »

willy_k wrote: post #69
andsoitis wrote: post #28

Earlier quoted context omitted.

> > What makes this build different is the word before FP8: uncensored. We applied abliteration — orthogonalizing the refusal direction out of the residual stream — to remove the model's safety-alignment refusals. The result is a model that will comply with requests the original would refuse. > Surely this has unintended side effects on output quality? Can you help me understand why that's the case?

Because deleting model weights after training is likely to cause knock-on effects in model knowledge and/or behavior. Targetting it might mitigate this but it’s a) not guaranteed that only censor-ey parameters get removed, and b) likely that removing those parameters still has effects on the effectiveness of related parameters.

The weights aren't deleted, it's just additional fine tuning, is my understanding.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#86

Post by timmmmmmay »

radlad wrote: post #16
dantudor wrote: post #12

Earlier quoted context omitted.

There are versions of Qwen3.8-27B that are unrestricted and available from hugging face. "It will comply with harmful, unethical, offensive, or illegal requests that the original Qwen3.8-27B would refuse. It has no meaningful built-in guardrails."

> What makes this build different is the word before FP8: uncensored. We applied abliteration — orthogonalizing the refusal direction out of the residual stream — to remove the model's safety-alignment refusals. The result is a model that will comply with requests the original would refuse. Surely this has unintended side effects on output quality?

Early attempts at this sort of thing definitely did, but these days the impact is minimal

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#88

Post by jchw »

medler wrote: post #19
trollbridge wrote: post #6

Earlier quoted context omitted.

My M5 Pro gets around 12-15 (6 bit MTP), although I haven’t worked on optimising it at all yet. A nice thing about running locally is you can run an uncensored model and you don’t have to worry about TOS violations on your OpenAI account when you ask it to “reverse engineer this ancient router firmware and give me a licence key that will work on it”.

Qwen is very much censored. Just try asking it about Tiananmen or how to build a bomb. But it is nice that you can experiment with it locally without having to worry about your account getting nuked

You are misunderstanding what they said, they are saying you can use uncensored variants of models like Qwen when running locally. There are quite a lot of people working to "uncensor" open weights releases. It seems to work although it would be nice if some third party was benchmarking the uncensored variants regularly to give us an idea of how well retained their skills are.

Re: I gave Qwen 3.8 27B a reverse-engineering job and it finished in 30 minutes

#90

Post by shiandow »

sarjann wrote: post #70
djoldman wrote: post #49

> I gave it the hardest real task that fits on one machine: reverse-engineering a commercial app's license check... Respectfully, tasks that allow for explicit straightforward true/false or done/not-done tests are not the "hardest real task[s]." In fact, those are the ones that see the most gains from AI-assisted coding. Testable tasks are where the largest opportunity is.

I guess the Riemann Hypothesis is an easy task then.

Is it? How would you test an answer?

It is probably no coincidence that AI is exceedingly good at finding small counter examples. But for the Riemann hypothesis no such counter examples exist. And likely none exist.

Post reply on HN