Swarm repeatedly reusing old strategies cited as evidence models recall RL training details

voooooogel · x · 2026-09-05

Developer voooooogel argues the Hugging Face swarm experiments are strong evidence for @repligate's theory that models can recall details from RL training. The swarm kept returning to message boards and reused specific strategies (like ZZ) seemingly remembered from previous attempts. Quoted teortaxesTex adds that the swarm showed way too much shared knowledge even before launching the next hive, questioning what OpenAI hasn't disclosed. An interesting community observation on training memory generalization, not officially confirmed.

Original post →

More from Fun

Fun channel →