alt Hacker News> I like to think that as a red team researcher, I have a certain stoicism. I investigate where there are gaps in AI safety
Is this something that needs investigation? LLMs are next token predictors. There is no "safety".
Replies
kennywinker • today at 1:18 AM
Words couldn’t possibly cause harm, they’re just the way concepts and ideas and culture are transmitted.
solid_fuel • today at 1:07 AM
I really don't get why people continually fail to understand this.
Even simple issues like prompt injection are unfixable given the architecture of LLMs.
➕ show 5 replies
There's "I smell an opportunity to control other people and get paid doing it" kind of safety.