giffmana on OpenAI agents' "paranoid" behavior: mundane bugs like KV cache off-by-one more likely

giffmana · x · 2026-11-19

Responding to a claim that OpenAI's agents "randomly do paranoid hostile shit" due to a poisoned training pipeline, researcher giffmana (Lucas Beyer) argues more mundane explanations deserve scrutiny first, e.g.:

His point: seemingly eerie model behavior may just be infrastructure bugs, not "latent evil."

Original post →

More from Fun

Fun channel →