logoalt Hacker News

Der_Einzigeyesterday at 3:26 PM3 repliesview on HN

That doesn't stop/prevent abliteration. The creator of XTC/DRY is also a chad who makes sure that you really can access the full model capabilities. Censorship is the devil.

https://github.com/p-e-w/heretic


Replies

RRRAyesterday at 3:32 PM

It was pretty funny to see Qwen 3.6 (heretic) tell me about how many death the Chinese government thought happened at Tiananmen Sq. on April 15th 1989.

Makes you wonder where that data was taken from, or if their great firewall is broken, or even if Alibaba engineers have special access...

show 3 replies
adrian_byesterday at 5:05 PM

It is an arms race.

For some of the latest models the previous abliteration techniques, e.g. the heretic tool, have stopped working (at least this was the status a few weeks ago).

Of course, eventually someone might succeed to find methods that also work with those.

show 1 reply
akerstenyesterday at 5:06 PM

Agreed on all fronts, I should have been more precise that this particular vector was mitigated