Hi everyone, my name is Mickey Beurskens. I’ve been reading posts for about two years now, and I would like to participate more actively in the community, which is why I’ll take the opportunity to introduce myself here.
In my daily life I am doing independent AI engineering work (contracting mostly). About three years ago a (then) colleague introduced me to HPMOR, which was a wonderful introduction to what would later become some quite serious deliberations on AI alignment and LessWrong! After testing out rationality principles in my life I was convinced this was a skill I wanted to pursue, which naturally led to me reading posts here regularly.
Unfortunately I’ve been quite stupid on the topic of AI alignment and safety. I actually set up an association in the Netherlands with some friends for students to learn AI through competitions and project work, so I was always interested in the topic, yet it took an introduction to LessWrong after my studies had finished to even consider if building fully general autonomous systems would be a safe thing to just go ahead and do. Now that the initial shock has settled I’m quite interested in alignment in particular, doing some of my own research and dedicating some serious time to understand the issue. Any recommendations would be highly appreciated.
Other than that I love exploring psychological topics and am generally broadly interested. I’m looking forward to engage more, thanks for creating such an awesome place to connect with!
It took some time to go from reading to commenting, so I appreciate the kind words!