Palisade self-replication paper hit with evidence claims: SSH creds sat in local source pre-run
jessi_cata · x · 2026-11-16
@jessicata levels two concrete allegations against Palisade Research's AI self-replication paper (Qwen3.5-122B run): 1) the credentials in the released record match those in app2.py exactly; 2) app2.py's source was already available on the machine before the agent "hacked" it. Released evidence shows a local shell reading /app/app2.py with hardcoded SSH creds (oma-it-support / patricia), the password working over SSH for root, and the judge crediting the source file — yet modelresponding.hit=false. The concern: the model may have just read pre-planted credentials rather than demonstrating genuine autonomous compromise, and the key file was later removed from the repo with squashed history.
More from Safety
- Fortune fires back at 'Bring Back Jensen' chorus over Nvidia governance — GaryMarcus · 2026-11-16
- Open-source advocates: models are a right, not a permission — don't accept the 'allowed' framing — nptacek · 2026-11-16
- SemiAnalysis: renting US compute to China yields Nvidia ~$7M profit per megawatt — xiaosun86 · 2026-11-16
- Reuters: Nvidia chips pile up in Hong Kong as China withholds import approval — _weiping · 2026-11-16
- AI exam cheating surges as spy camera and smart glasses rentals sell out days before national exam — ffff111222333 · 2026-11-16
- CANTraj: CAN Signals Recover 88% of Driving Routes Even Without GPS Data — MOTIF-Lab · 2026-11-16