"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.
More from AGI Musings
- Roman Yampolskiy calls the AGI sprint a race to build God in podcast — MaxUnfried · 2026-09-18
- Gary Marcus: 'Rogue agents' is AI's excuse for irresponsibly built software — GaryMarcus · 2026-09-18
- yacine argues AI companies are uncontrolled super-entities eating employers — yacineMTB · 2026-09-18
- Roman Yampolskiy returns to DOAC to update his AI safety warning that reached 20M+ viewers — MaxUnfried · 2026-09-18
- Ex-OpenAI's Yacine: enterprises are the next thinking machines — learn AI or get eaten — yacineMTB · 2026-09-18
- yacineMTB Predicts AI Tech Is Too Powerful for a Few to Control — yacineMTB · 2026-09-18