Someone should put out a library & API for mech interp of open source models and transparency-mog Dario
Anthropic CEO:
“open source is kind of a distraction you still can’t really see what’s happening inside the model, so it’s not truly “free.”
People should be paying a lot more attention to what Anthropic is doing.
Users supported urging mechanistic interpretability tools for open source models because they find the topic very interesting and back any move to outpace Dario.
No Digg Deeper questions have been answered for this story yet.
Maybe @GoodfireAI ?
Someone should put out a library & API for mech interp of open source models and transparency-mog Dario
@beffjezos "You can fine tune the model['s rejection parameters]"
@beffjezos I support any mogging of Dario
@beffjezos absolutely, interpretability is actually very very interesting