3 claims in “philosophy of science, methodology”
Feynman disliked thinking that 'floats off' into word-batting without grounding in concrete steps or understanding, preferring ideas anchored in calculable foundations where one could trace the reasoning through to justified conclusions.
Powerful analogies work because one domain has been well-developed (over ~100 years of research with much known) while another is fresh and underdeveloped; mature concepts can be imported into the less-developed area, allowing rapid 'physicalization' and advancement comparable to the mature domain.
Physics as a discipline makes progress by simplifying the world, ignoring complications, and putting them back later. This approach (inherited from Galileo) works well for physics and cosmology, but breaks down in fields like psychology and sociology where interactions and emergent properties are crucial to the phenomena.