> As we focus more on memory, we also need to think about strategic forgetting. Over time, overly precise memories become conflicted and messy, and nobody has yet figured out how to handle this.

> I think that’s the context problem of tomorrow.

This passage is pretty thought provoking and maybe explains why humans have imperfect memory. Perhaps the perfect memory we wish LLMs to have impedes creativity and is maladaptive.

Besides - we already have machines with perfect memory: computers themselves.

Strategic forgetting helps put the non-deterministic machine to best use.

I liked how this justifies the continuing relevance of context engineering, and how it coexists with trends like loop engineering.