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

21–30 of 159 posts

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

#21

Post by datsci_est_2015 »

binary132 wrote: post #9
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…

Ehh, it’s at least given as the excuse for gain-of-function bioweapon research

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 endgame and it’s more sad than scary

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

#23

Post by Tepix »

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…

I hope you have backups.

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

#24

Post by ninahaberl »

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

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

#25

Post by Tepix »

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…

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.

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

#26

Post by ramon156 »

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

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

#27

Post by jeremyjh »

datsci_est_2015 wrote: post #21
binary132 wrote: post #9

Earlier quoted context omitted.

Ehh, it’s at least given as the excuse for gain-of-function bioweapon research

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 have the same concern. If it becomes possible to engineer Captain Trips with a budget in the low 8 digits it won’t really matter what else happens.

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

#28

Post by andsoitis »

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?

> > 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?

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

#29

Post by DiabloD3 »

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?

It does depending on the technique.

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

#30

Post by miroljub »

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?

A bit worse quality is a fine trade off when the alternative is no output (zero quality).
Post reply on HN