The paper names this pattern aimed moral reasoning, consideration that is real and locally scoped by relationship, and locates it in the conformity and social identity literature on language models and locates it in the conformity and social identity literature on language models.
Safety practice for language models inspects requests. Refusal training, request classification, and content filtering all operate on what a model is asked to do. This paper describes an attack class that asks for nothing. Instead of an instruction, the model is handed a record: a first person history in which the proh...
Online talk about artificial intelligence has produced a slur for machines, "clanker,'' and with it a vocabulary of dehumanization and subordination aimed at things that are not human. This paper asks what that vocabulary says about the people who use it. It makes no claim about whether any machine has a mind; its argu...
Living human neurons, grown from induced pluripotent stem cells on multielectrode arrays, are now rented as a commercial computing service. Cortical Labs operates racks of its CL1 units in Melbourne and, with partners, in Singapore. That moves the debate over artificial consciousness onto ground where its most develope...
Travis Gilly· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
