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

111–120 of 159 posts

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

#111

Post by matheusmoreira »

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.

I'm a hobbyist and I got in. Just filled in the form.

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

#112

Post by hghnncrh »

cyanydeez wrote: post #62
tempest_ wrote: post #51

Earlier quoted context omitted.

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.

I've included docs and tests as part of my vibe coding endevours. It doesn't matter if either is litterally correct, but they create guardrails for future context to prevent regresssions and blind avenues, etc. It's fairly successful but hits the time constrains and reduces the "value" of getting a local model to develop software. It's still a bump in productivity.

how do incorrect tests or docs help create correct guardrails?

if your tests and docs are possibly incorrect, and you're not writing the code.. how do you know if it even works? for extremely simple software you can just use it but for anything with access to disk or the network or with user options...

you sound psychotic. actually. so nevermind, LLM psychosis is extremely common on this website, that's def all that's happening here

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

#113

Post by egl2020 »

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...".

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

#114

Post by TofuLover »

laidoffamazon wrote: post #107
TofuLover wrote: post #31

Earlier quoted context omitted.

Completely coincidentally, we're just about to launch a service that does exactly this (API access to uncensored open models)! We have a waitlist at the moment but will be live very soon! https://violentdelights.ai

I really like this product idea but I really don’t want “violent delights” on my credit card that sounds extremely suspicious

Er, yes, good point! We'll make sure billing is a bit more discreet than that!

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

#115

Post by shujito »

TofuLover wrote: post #114
laidoffamazon wrote: post #107

Earlier quoted context omitted.

I really like this product idea but I really don’t want “violent delights” on my credit card that sounds extremely suspicious

Er, yes, good point! We'll make sure billing is a bit more discreet than that!

name it "virtual" instead ;)

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

#116

Post by Ohentis »

shiandow wrote: post #90
sarjann wrote: post #70

Earlier quoted context omitted.

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.

An answer would be a proof that either it holds, or that it doesn't hold. You would test such an answer with an automated proof checker (probably lean).

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

#117

Post by verdverm »

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.

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?

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

#118

Post by verdverm »

colingauvin wrote: post #82
Neywiny wrote: post #43

Earlier quoted context omitted.

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

if you download them, you can remove all internet access for the model going forward on the task, don't want to http proxy like OpenAi now do we?

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

#119

Post by verdverm »

saidinesh5 wrote: post #4

Lately I genuinely believe that the future will be large frontier models generating and updating inputs/skills for "good enough" local models to solve our daily problems. A lot of tasks which need a bit of intelligence don't really need that much compute. Just good enough documentation / skills, tool calling and a good enough local model. Not sure what exactly this means for all those data centers that are getting bu…

The data centers are for inference time serving, and as long as the GPUs go better, it shouldn't really matter. Token prices should go down 10-100x over the coming years, and then we will use more, because they have more capacity for the same hardware

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

#120

Post by AdamConwayIE »

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.

Not sure to be honest. I have a couple of CVEs and also linked a talk I had presented as it mentioned those as an example. Got approved in a few minutes.
Post reply on HN