Kind of, but that's not inherent to the over reliance on memorization. I suspect using the top tier models from any of OAI, Anthropic, or Google would have resulted in much less embarrassing results, and I believe they're all primarily memorizers, not generalizers.

The search issue happened because Google had to use a really cheap model to power the search results, and a memorizing model that cheap is going to be highly constrained in capabilities (at least right now).