Comment on A research scientist at Anthropic has been using LLMs to black hat software and he's spooked

<- View Parent
fallaciousBasis@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

As I recall Go players have adapted and have found ways to induce hallucinations and beat the machine, some using other AI. Others have adopted “adversarial strategies.”

arxiv.org/abs/2211.00241

They say it’s comprehensible enough that a human “expert” can do it without algorithmic assistance.

source
Sort:hotnewtop