Hacker News

points by ollin 1 day ago | 0 comments

I think it's from lyra's neuron-explorer project https://x.com/_lyraaaa_/status/2113833330429083662 (see also https://neuronary.org/about, https://github.com/lyramakesmusic/neuron-explorer)

[–] fy20 1 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 23 hours ago

Are you thinking of this one?

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

About halfway down they inject bread into its head.

[–] noddybear 19 hours ago

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

[–] square_usual 18 hours ago

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

[–] tough 22 hours ago

mcnamara / goodfire couple weeks ago