Remix.run Logo
▲ fy20 a day ago

There was a paper that popped up a month or two ago (I think published earlier though) about being able to inject "thoughts" into the neurons. E.g. Ask it what I should eat, and steer it towards "bread".

▲krackers a day ago | parent | next [-]

Are you thinking of this one?

https://www.anthropic.com/research/introspection

About halfway down they inject bread into its head.

▲noddybear 18 hours ago | parent | prev | next [-]

This stuff (activation steering) has been around for a few years at this point

▲square_usual 17 hours ago | parent [-]

Yeah, Golden Gate claude was in 2024! But I think the most recent/relevant thing was the monosemanticity discovery.

▲tough 21 hours ago | parent | prev [-]

mcnamara / goodfire couple weeks ago