I have a pretty fundamental concern with these sorts of techniques as a mechanism for eventually assessing alignment
that would lead to safety or alignment goodharting problem.
Hi. Thanks for mentioning us.
Unlike main labs or companies in China, we are doing fundamental research work on the ontological crisis problem with model theory from mathematical logic trying to set a new base for analyzing and preventing the crisis.
Due to our lacking of funding and restricted intellectual resources, the process is slower, but we will share our work when ready.
Mention a recent interesting work here: On the Complexity of Computing Markov Perfect Equilibrium in General-Sum Stochastic Games gave a related analysis on the comuting of Markov PE for RL agents.
https://www.lesswrong.com/posts/3eAstSeZthYh2o6sh/ai-safety-through-operational-physics-why-resource?utm_campaign=post_share&utm_source=link