Representation Engineering: A Top-Down Approach to AI Transparency

In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience. RepE places population-level representations, r… Read more

Similar

I made an AI to see the future

We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using twitter.com. You can see a list of supported browsers in our Help Center. (more…)

Read more »