The previous two posts have emphasized some problematic scenarios for mech-interp. Mech-interp is our example of a more general problem in AI safety. In this post we zoom out to that more general problem, before proposing our solution. We can characterize the more general problem, inherent in the causal–mechanistic paradigm,...
Loosely inspired by a submission to a hackathon on Autostructures, which is about radical transformations from even mildly intelligent AI. Previously, I've briefly alluded to 6 infrastructural pillars for an era where "things that don't scale" start to scale. This post is mainly aimed at conveying an idea of the...
This is an excerpt from the Introduction section to a book-length project that was kicked off as a response to the framing of the essay competition on the Automation of Wisdom and Philosophy. Many unrelated-seeming threads open in this post, that will come together by the end of the overall...
Fluid interfaces for sensemaking at pace with AI development. * Register interest here for the workshop in November 2024 (or to be invited to future workshops). To know some practical details, go to section 2. * Click here to help raise funds for the workshop and related events. * Apply...
Acknowledgements The vision here was midwifed originally in the wild and gentle radiance that is Abram's company (though essentially none of the content is explicitly his). The PIBBSS-spirit has been infused in this work from before it began (may it infuse us all), as have meetings with the Agent Foundations...