We aim to connect Rationalists from Karlsruhe (Germany) and surrounding areas. We are always happy to get to know new people and new perspectives(!). Please feel free to drop by even if you are unsure, feel awkward about it, or are not 'the typical LessWrong / SSC reader'.
This week, we will have an introductory talk on technical AI safety. It will introduce AI safety from first principles: What is AI safety, and what does it entail beyond alignment? Why are deep neural networks hard to understand, control and align in the first place? What technical solutions do we have to make AI systems safer?
The schedule will roughly be the following:
18:50 - 19:10: Soft beginning, socializing
introductions (in case of new attendees), Updates (what surprises did you encounter recently / what are your biggest updates? / what did you personally learn?)
~19:20: Beginner-friendly introduction to AI safety
We aim to connect Rationalists from Karlsruhe (Germany) and surrounding areas. We are always happy to get to know new people and new perspectives(!). Please feel free to drop by even if you are unsure, feel awkward about it, or are not 'the typical LessWrong / SSC reader'.
This week, we will have an introductory talk on technical AI safety. It will introduce AI safety from first principles: What is AI safety, and what does it entail beyond alignment? Why are deep neural networks hard to understand, control and align in the first place? What technical solutions do we have to make AI systems safer?
The schedule will roughly be the following:
18:50 - 19:10: Soft beginning, socializing introductions (in case of new attendees), Updates (what surprises did you encounter recently / what are your biggest updates? / what did you personally learn?)
~19:20: Beginner-friendly introduction to AI safety
~ 20:00: Open-ended discussion
Posted on: