←back to thread

Heretic: Automatic censorship removal for language models

(github.com)
745 points melded | 4 comments | 16 Nov 25 15:00 UTC | HN request time: 0.874s | source
Show context
joshcsimmons ◴[16 Nov 25 17:37 UTC] No.45946838[source]▶
This is extremely important work thank you for sharing it. We are in the process of giving up our own moral standing in favor of taking on the ones imbued into LLMs by their creators. This is a worrying trend that will totally wipe out intellectual diversity.
replies(13): >>45947071 #>>45947114 #>>45947172 #>>45947465 #>>45947562 #>>45947687 #>>45947790 #>>45948200 #>>45948217 #>>45948706 #>>45948934 #>>45949078 #>>45976528 #
1. SalmoShalazar ◴[16 Nov 25 22:33 UTC] No.45949078[source]▶
Okay let’s calm down a bit. “Extremely important” is hyperbolic. This is novel, sure, but practically jailbreaking an LLM to say naughty things is basically worthless. LLMs are not good for anything of worth to society other than writing code and summarizing existing text.
replies(1): >>45949167 #
2. int_19h ◴[16 Nov 25 22:47 UTC] No.45949167[source]▶
A censored LLM might refuse to summarize text because it deems it offensive.
replies(1): >>45959416 #
3. blackqueeriroh ◴[17 Nov 25 22:59 UTC] No.45959416[source]▶
An LLM cannot “deem” anything.
replies(1): >>45961761 #
4. int_19h ◴[18 Nov 25 05:42 UTC] No.45961761{3}[source]▶
I'm not interested in sophistry. You know perfectly well what I mean, and so does everyone else.