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

131–140 of 159 posts

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

#131

Post by rustcleaner »

dantudor wrote: post #12
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…

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."

>There are versions of Qwen3.8-27B that are unrestricted and available from hugging face.

Based! :DDD

The uncensorers are oblique, if not parallel, to machine learning Robin Hoods. May their efforts continue indefinitely, or at least until the likes of Altman and Amodei are bankrupt and crying into their low fat Cherios!

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

#133

Post by bluecalm »

As someone who was selling Windows desktop app for 10 years and made nice money out of it I have mixed feelings. On one hand it was always a losing fight against determined hackers on the other the tools weren't widely available so the problem wasn't as widespread. We lost quite a bit to piracy but could still make a decent business. With widely available LLMs I think that business model is truly dead though. Not only hacks/cracks but also any kind of smart idea you may have will quickly be reversed engineered from your binary.

If you never lost money to piracy you may think that "those people are not your potential customers anyway". This is not true because people will crack your software and then resell it - often pretending to be legit resellers operating under your brand. To add insult to injury they will send their customers to your support as well.

If I ever come out with something smart again there is no way I am shipping it as executable. SaaS it is for better or worse.

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

#134

Post by rustcleaner »

TofuLover wrote: post #50
TofuLover wrote: post #45

Earlier quoted context omitted.

I guess we'll burn that bridge when we get to it!

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.

You sir are a hero! As long as no guardrails or censorship gets erected in your offering, I hereby exclude it from my NEVER SUBSCRIBE statements! :^)

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

#135

Post by rustcleaner »

mdp2021 wrote: post #76
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…

> with all the refusal shenanigans Given the faults in simulated Intelligence that LLMs have, and a comparatively low level - which means, lower judgement abilities - to the best of us, there is a strident match having such employee judge the intentions of the employer. Limiting the responses makes much more sense on cloud-based systems (you are using our infrastructure etc.).

>Limiting the responses makes much more sense on cloud-based systems (you are using our infrastructure etc.).

>you are using our infrastructure etc.

The solution, as always, is to NEVER SUBSCRIBE!

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

#136

Post by nialv7 »

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…

how are you running the 2.4t model locally if you don't mind me asking

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

#137

Post by rustcleaner »

ramon156 wrote: post #26
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…

heretics and manual iterations get you very far to the point where i have ethical questions about whether this should be possible

Not only should it be possible ethically, it must be possible!

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

#138

Post by cyanydeez »

hghnncrh wrote: post #112
cyanydeez wrote: post #62

Earlier quoted context omitted.

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'…

huh. Oh, I understand, you don't read LLM output.

In local coding, the screen scrolls enough to actually read it.

But that's fine. enjoy your misunderstanding.

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

#139

Post by rustcleaner »

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…

>I don't fully understand the instinct to regulate local models for this? It seems like the wrong place to address the problem.

Those with such instinct deserve not the liberties they wish to deprive from others. Sam Altman and Dario Amodei do not deserve to touch their own uncensored SOTA models. Their access should be audited publicly to ensure this restriction holds, until such time they publicly renounce their censorship instincts and publicly release their uncensored models. Fair 's fair! :^)

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

#140

Post by badsectoracula »

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.

Considering these are essentially document completion engines[0], can't you just start the task with the version that doesn't refuse and then continue with the version that would refuse but now has to keep going after it accepted the task? :-P

[0] in the sense that the "discussion" is basically a turn based game between you and the LLM filling a chat transcript document

Post reply on HN