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

121–130 of 159 posts

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

#121

Post by b112 »

generalizations wrote: post #91
AdamConwayIE wrote: post #61

Earlier quoted context omitted.

Maybe so, but there were other elements that I've seen frontier models struggle with in the past, which was the perspective I had coming into this. It's the type of test I run frequently and this is the first small local model I've seen pull it off. It had a very non-standard RSA key implementation that was obfuscated heavily. As well, it has an online license check at first run, and that part typically trips up most…

How hard is it to get access to the Anthropic Cybersecurity program? That’s gotta be rough.

You have to use Persona to ID, so take that into account.

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

#122

Post by ErroneousBosh »

tempest_ wrote: post #51
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.

Which is exactly why we saw 1000s of ' "I" rewrote in rust' posts last year when agentic coding really took off. Agents (even ones powered by small models) do reasonably well when provided an oracle to work against.

> when provided an oracle to work against.

You mean when the cocaine piracy parrot has something to plagiarise?

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

#123

Post by rustcleaner »

mdp2021 wrote: post #81

> 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…

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

They shouldn't. They should fail. Their philosophy is to deny you local capabilities* and charge you for access to theirs through whatever moral filters they deem neccessary. Every subscriber to OpenAI and Anthropic is helping them continue to damage our economy and individual sovereignties. A hammer should never refuse its wielder.

Unguardrailed AI today is like hard cryptography in Phillip Zimmerman's time. We need an AI second amendment before the ultrawealthy parasite moralizers totally own us!

NEVER, EVER SUBSCRIBE! NO CLOUD, NO STREAMING, AND NO AI!

You are not sovereign if it's not local and in your control.

*(Sam Altman's cornering of DRAM in a Hunt Brothers like manner. Dario's belief that public access to unguardrailed AI is a sin.)

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

#124

Post by giancarlostoro »

verdverm wrote: post #117
giancarlostoro wrote: post #103

Earlier quoted context omitted.

How can I use AI to do real security audits anymore if they don’t trust people in an enterprise plan? Its useless.

Trust is a two way street, why do you trust them (Ant) if they do not trust you? Have they done enough shady things yet to break it? Are their models really that far ahead it's worth it?

Yes, if you use Fable for anything (which is their best security model) they send all your IP and prompts to be reviewed.

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

#125

Post by rustcleaner »

giancarlostoro wrote: post #103
mdp2021 wrote: post #81

> 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…

How can I use AI to do real security audits anymore if they don’t trust people in an enterprise plan? Its useless.

The answer is to NEVER SUBSCRIBE, let the datacenters go the way of dark fiber after the '90s telecom bubble collapse. Maybe also a nice fat 90% corporate income tax on rentier-like businesses (subscriptions based: like SaaS, AI resellers, non-perpetual licensers, cloud storage and compute, etc). Force businesses with tax policy to only operate in a sell once + works forever, business model. Those who wish to rentier will need to spend the income on hiring more employees or put it into R&D, but the tax slides in after costs but before dividends or stock buybacks. :^)

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

#126

Post by naasking »

egl2020 wrote: post #113
VulgarExigency wrote: post #5

> The first attempt at recovering the key was wrong in a very specific way; it produced a working key and the signature check passed, but a hash the binary computes as an integrity check didn't match. In my experience, most models would have called it done and left it at that, but Qwen 3.8 27B didn't do that. Instead, it highlighted the mismatch, went back to the drawing board, and kept going until the value matched…

Any idea how being persistent is trained? I've noticed that telling an LLM that it needs to think some more sometimes produces better results, but the claim here is that "they are very persistent" and "...kept going...".

It's from work like this:

https://arxiv.org/abs/2309.11495

A RL pipeline can reinforce verification behaviour even better than simple prompting.

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

#127

Post by naasking »

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.

> Respectfully, tasks that allow for explicit straightforward true/false or done/not-done tests are not the "hardest real task[s]."

Counterpoint: P vs. NP.

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

#128

Post by rustcleaner »

ninahaberl wrote: post #24
exceptione wrote: post #8

Local models would be even better if they did not ship with all the refusal shenanigans built-in. You can safely bet organized crime has access to the best models without these hoops, which makes the case that the average user (=non-criminal) should have access too. As I understood from an ex-Anthropic employee, some orgs got access to Mythos based on their high enough spending level, not on other grounds. Either we…

I’d expect these shenanigans to get much worse over time for the average Joe. Imagine a world where any random person can run a super-capable model on their own hardware with no limitations and no one to pull the plug. Information has always been power and those who already have power won't just allow everyone else having the same tools as them

>Imagine a world where any random person can run a super-capable model on their own hardware with no limitations and no one to pull the plug.

That would be my heaven. I wish that for you and Joe down the street, as much as I wish it for myself! I would fight and even die to defend your right to free compute. Will you do the same for me, brother?

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

#129

Post by naasking »

jszymborski wrote: post #85
willy_k wrote: post #69

Earlier quoted context omitted.

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.

There is no question model quality is degraded by this though.

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

#130

Post by naasking »

Zambyte wrote: post #80
weberer wrote: post #68

Earlier quoted context omitted.

What can a LLM generate that's illegal in the USA? Specifically a text-only LLM?

Blackmail, incitement, libel, and basically anything that comes up if you search "computer crimes".

Generating blackmail is not illegal, using it to blackmail someone is. Generating libel is not illegal, publishing it publicly is not illegal either although you can be sued over it.

Generating worms and computer viruses is not illegal last I checked, but disseminating them is.

Post reply on HN