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

101–110 of 159 posts

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

#101

Post by colingauvin »

33dd wrote: post #36
Tepix wrote: post #25

Earlier quoted context omitted.

With AI being more useful with access to more of your data, I can't see myself using cloud AI models for purposes such as personal assistants. Perhaps with differential privacy or confidential compute... But ideally these models run locally.

This is just lazy thinking. E.g. having an agent that alerts you when subscriptions are close to renewal etc - yeah seems easy to understand / see happening on the surface. Until you get into the implementation details and realise 'yeah errr. not gonna work'. That openclaw nonsense is an example of this.

Which implementation details? I very much already have this, today.

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

#102

Post by weberer »

vunderba wrote: post #92
weberer wrote: post #75

Earlier quoted context omitted.

That's not illegal in any way.

https://www.theguardian.com/us-news/ng-interactive/2026/jun/... Legality was never ICE's strong suit.

Its amazing how biased that source is and how much it buried the lede. They were arrested for participating in a riot where someone attempted to murder a police officer. That's not just someone criticizing ICE on social media. If it was, half the posters in any political thread on HN would already be arrested.

https://www.justice.gov/opa/pr/antifa-cell-members-convicted...

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

#103

Post by giancarlostoro »

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.

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

#104

Post by geye1234 »

I'm far from being an engineer, but I can code a bit and have an engineering-adjacent role, and 3.8 27B "seems" -- purely subjectively -- miles ahead of 3.6 for the medium-difficulty tasks I give it. In particular, it's only started looping once in the 2 weeks or so I've had it. 3.6 did so every day.

I normally run with thinking low but it's still miles ahead.

I had been annoyed at not being able to run 0731 locally, but now I'm not sure I need it. I think I could leave 3.8 running overnight without waking up to find my office sweltering at 80F and seeing eternal loops on my screen.

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

#105

Post by jchw »

AdamConwayIE wrote: post #40
jchw wrote: post #3

I'd personally like to know more about what tools it used/wanted and the harness setup, because this sounds pretty cool. I have a dual Arc Pro B70 setup and currently get around 22 t/s which isn't great but isn't terrible either (it is at least less quantized.) I've seen GPT 5.6 Sol happily invoke objdump and even write jobs to run headlessly which Ghidra when trying to disassemble a binary.

I added a line to address this, sorry it wasn't there before! It was Pi and only used Bash-based tools.

Cool. I was thinking of running Qwen3.8 through Codex, but maybe it's time I take a look at Pi.

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

#106

Post by generalizations »

Daviey wrote: post #98
generalizations wrote: post #91

Earlier quoted context omitted.

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

It was surprisingly easy for me to be approved in their CVP programme as an independent security researcher, that said, abliterated Qwen3.8-27B model feels better and cheaper.

Nice. Though it sounds like you have to already have some creds under your belt first.

What quant and what abliteration of qwen 3.8 27b has worked for you? I'm concerned that too much quantization and it can't do the work anymore.

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

#107

Post by laidoffamazon »

TofuLover wrote: post #31
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…

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

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

#108

Post by dackdel »

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.

as he rightly says, fuck all benchmarks and metric as long as it can get done. who cares what it specifically good at or not and trying to create benchmarks as long as it solves .

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

#109

Post by datsci_est_2015 »

xyzzy123 wrote: post #54
datsci_est_2015 wrote: post #21

Earlier quoted context omitted.

Digression, but this is the real Great Filter imo, not AI. I think technology advances to a point where it only takes one or two bad actors to type the right prompt to get a recipe for civilization-destroying bioweapons before you get anywhere near true AGI or anything relevant to the Kardashev scale. Biology is fragile. But not that that’s a good justification for hamstrung models. I think it’s just the inevitable e…

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…

Yeah I was thinking more on the scale of nation-state level actors. Most leaders would not consider a bio weapon due to potential blowback on their own population, as they generally don’t want to be the leader of a nation of corpses and ashes.

But if they don’t care, or if they already are the leader of a nation of corpses and ashes, maybe there’s not so much holding them back.

In my layman’s perspective, bio weapons seem to be more dangerous and volatile than nuclear weapons. And increasingly easier to engineer as biotech advances. I think about the headlines of “microscopic robots that target tumors from within your body” and see the horrifying opposite side of the double-edged sword.

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

#110

Post by Refefer »

jnwatson wrote: post #100

I can't get Qwen 3.8 27B to do a simple code review on a fairly basic Python file. With thinking on it just ruminates forever and with thinking off it gives obviously bad borderline hallucinating advice. Edit: I tried again with the 2.4T model and it still ruminates to death, but with thinking turned off, it generated genuinely useful advice. Edit2: adding --reasoning-budget 8000 --reasoning-budget-message "Reasoning…

One of the big learnings from 3.8 27b is adding reasoning budget really hurts the model. you need to let it spin for as many thinking tokens as it wants to to get it out. Another big takeaway is reasoning effort set to low doesn't save you tokens: low is pretty uncertain about things so it ends up thinking more (you can find some tests from folks on youtube). The final question, as always, is what quant are you running it at? KLD matters _a lot_ when it comes to its performance and it especially manifests with MTP/DFlash acceptance rate which makes those long thinking traces take a long time.
Post reply on HN