This is a quick post to mention that I'll be in Berkeley attending the SERI MATS program to work on aligning language models. At the time of writing, my research will likely involve studying ways to make language models valuable for accelerating alignment (like distillations) and running experiments to see how things go. This work will directly feed into my more practical work of building tools for other alignment researchers (or people trying to enter the field).
If you are in Berkeley during the next 2 months, let me know, I'd love to meet people over coffee or a drink. Potential collaborations would be amazing too!
Also, EAG SF is next week so if you attending, don't be shy to say hello!