unexposedhazard

There was a great talk by those hackers at the CCC congress a while back where this story was originally published. Its fairly in depth, showing everything they did to get past the DRM and stuff.

https://media.ccc.de/v/37c3-12142-breaking_drm_in_polish_trains

https://www.youtube.com/watch?v=XrlrbfGZo2k

Itch.io already went and hid all adult content afaik, so we are already past the first stage even.

For me it was the opposite. I somehow immediately understood what happened, but was just confused why tf anyone would do that. Then i saw the RPG.

Idk what was meant by this one, but they keep pushing updates that break preexisting setups. This would be fine if admins were sufficiently warned and they added proper info about breaking changes to their changelogs, but they simply havent done that.

Shouldnt have deleted it. Would have been a power play.

China is still happy to deliver new parts tho afaik

Nice short but informative write up. Policy servers are hugely needed, considering the horrible gore and CSAM spam waves i experienced in some very big public rooms.

Imagine having a tail so big and floofy that u can use it as a pillow. Amazing.

Thats why i asked the previous commenter to provide a source for the debunking so we dont have to keep guessing. Seems like it was indeed entirely fake. https://www.theverge.com/news/713385/zohran-mamdani-instagram-suspended-debunk

Yeah it probably just absorbed all the moisture on your lip and glued itself to it because of that.

purposely putting extreme effort into tricking the LLM into saying something harmful

I dont think you understand how many mentally unstable people out there are using LLMs as therapists.
There are fuckloads of cases now of people that were genuinely misled by LLMs into doing horrible things.

I agree with your sentiment, but the thing is that the companies are selling their shit as gold and not as shit. If they were honest about their stuff being shit, then people wouldnt be able to capitalize off of malicious prompt engineering. If you claim "we made it super safe and stuff" then you are inviting people to test that.

I would generally not make companies responsible for how users misuse their products, but OpenAI is basically doing everything to get people to misuse it. They are overselling it so hard i think its reasonable to sue them for it.