"Looping on an LLM core" agent architecture is deeply flawed, argues dev

GaryMarcus · x · 2026-09-18

In a reply to Gary Marcus, developer Romeo Lupascu argues that the prevailing agent architecture — looping on an LLM core while piling onto the same context — is deeply flawed and should be scrapped and rethought. A one-line opinion, but representative of ongoing skepticism about mainstream agent design.

Original post →

More from AGI Musings

AGI Musings channel →