←back to thread

Uncensor any LLM with abliteration

(huggingface.co)
586 points mizzao | 1 comments | 13 Jun 24 03:42 UTC | HN request time: 0.226s | source
Show context
vasco ◴[13 Jun 24 06:49 UTC] No.40666684[source]▶
> "As an AI assistant, I cannot help you." While this safety feature is crucial for preventing misuse,

What is the safety added by this? What is unsafe about a computer giving you answers?

replies(11): >>40666709 #>>40666828 #>>40666835 #>>40666890 #>>40666984 #>>40666992 #>>40667025 #>>40667243 #>>40667633 #>>40669842 #>>40670809 #
1. CGamesPlay ◴[13 Jun 24 06:51 UTC] No.40666709[source]▶
It's unsafe for the publisher of the model to have their model perform "undesirable" action, because it leads to bad PR for them. In this case, Meta doesn't want a news article that says "Llama 3 gives instructions to stalk your ex" or something along those lines.

With this "uncensoring", they can say, "no, an unaffiliated product offered these directions; Llama 3 as provided does not."