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

31–40 of 159 posts

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

#31

Post by TofuLover »

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

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

#32

Post by radlad »

miroljub wrote: post #30
radlad wrote: post #16

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?

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

On censored inputs only.

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

#33

Post by cromka »

catlifeonmars wrote: post #18
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…

What’s the fundamental difference between a frontier model and a local model anyway?

Privacy!

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

#34

Post by mark_l_watson »

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…

Yes! My main use of very strong models is in writing my own coding harnesses for small local models, tailored for my needs. I also use very strong models to get much smaller skill files and also writing tools for my harnesses.

re: data centers: pump and dump. Wealthy investors will have made their money and walked away, and the corrupt democrat and republican politicians in Washington will, as usual, protect the interests of the ultra wealthy and leave the general public to pay for poor decisions. There will be a government bailout.

Anyway, on a positive note, I am all in for small local models that are augmented by strong hosted models for specific tasks. Use technology to help people, not make billionaires even more money.

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

#36

Post by 33dd »

Tepix wrote: post #25
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.

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.

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

#37

Post by UI_at_80x24 »

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

Given the context, your domain name is 'chefs kiss', perfect.

I am completely curious what your legal defense would be though.

"Come do things with AI that are probably illegal!"

What?! We had no idea people would do things that are illegal!

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

#38

Post by AdamConwayIE »

topper00_raptor wrote: post #10

Why does the screenshot on your pi terminal shows opus-4.6-medium from your claude subscription ? Instead of Qwen ?

Ah, my bad! This image came from our backend, used for an unrelated article. I selected it by mistake rather than inserting the actual image that I'd uploaded. I'm updating it, thanks for the heads up!

For what it's worth, that image couldn't have been related. The other screenshots all showed thinking traces, and Claude doesn't share those.

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

#40

Post by AdamConwayIE »

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.
Post reply on HN