but then I want to express ideas like “I don’t just want to think the tree I planted is healthy, I want the actual tree to be healthy”. Which sure is tricky, if “the tree” is a latent variable in my world model, a high-level abstract concept, and we don’t have a general way to map my own internal latent variables to structures in the environment.
Thanks for this great post!
This might interest you—my work in RLFC is not a general way to map internal latent variables but by using a chain of data sets (or framework continuums) I’m able to test the concepts I predicted[1] a pre-trained model (gpt2xl in this experiment) learned during pre-training. Also, the same method allows the model to optimise itself to any instructions included in the same data set. You can read it here.
Thanks for this great post!
This might interest you—my work in RLFC is not a general way to map internal latent variables but by using a chain of data sets (or framework continuums) I’m able to test the concepts I predicted[1] a pre-trained model (gpt2xl in this experiment) learned during pre-training. Also, the same method allows the model to optimise itself to any instructions included in the same data set. You can read it here.
If a pre-trained model is capable of a complex transfer learning, it is possible to reorganize the abstractions inside that model.