EA Miami will be doing a follow up workshop on AI safety, this time focusing a little more on the technical details. In particular, we will be discussing mechanistic interpretability as a mitigation strategy and prompt hacking as a risk factor. We'll also be talking about economic disruption due to AI / Robotics. No technical background is necessary, just come with an open and curious mind!
There will be lots of room for discussion and questions so please feel free to join and participate! No prior knowledge is needed, and we encourage you to attend if you feel uncertain.
When: Saturday, June 21 from 1-3 p.m.
Where: Coconut Grove Branch Library @ 2875 McFarlane Rd, Miami, FL 33133
To stay up to date on future events and updates, sign up for our newsletter: https://subscribepage.io/effectivealtruismmiami
Posted on: