new post on harness engineering for AI self-improvement: https://t.co/ZYvGfVs61k
It is hard to forecast how much the future of RSI will rely on harnesses. Likely harness engineering will evolve in the direction of self-improvement and enable auto-research, and, in turn, smarter models keeps harnesses simple.
Even when many harness improvement get eventually internalized into core model, the need to specify goals and context will not disappear.
My slides on "Steering Generative Models: From Mathematics to Biomolecular Design"
https://t.co/HSaTulQItQ
I gave this presentation yesterday at ChemAI (https://t.co/AWmfl1wWLB) – an incredible event bridging the worlds of AI and Chemistry!
Many thanks to Kathleen Hinge, Stefano Martiniani, Yingkai Zhang, Mark Tuckerman, and Glen Hocky for amazing organization and for inviting me!