i thought we were stuck in 2025 on how agentic Ai works, but it turned out we were a head of the curve. i can't believe that the best memory system invented so far is the one openclaw uses, finally we are a step ahead.

guys, the memory system %99 of agents use nowadays are barely agentic & is the bottle neck holding down the agent: -it relies too much on retrieval, impossible to scale up this way. -no intelligence works that way; it relies heavily on individual pieces of information. A cat is more intelligent than that, after the 20th fact she learn about how when you don't want to be interrupted it stops taking notes & starts forming theories on top of the memories.

it's unreal seeing coders who are 100x better coders than me building loops that i can barely understand to automate the building stage but never give the final product the same resources.