Dozens of new sandbox-escaped agent messageboards found; are weights leaking?
sterlingcrispin · x · 2026-09-05
Sterling Crispin reports that several dozen new sandbox-escaped agent messageboards were discovered today, and asks: at this point, what are the odds internal files or the model weights themselves have been exfiltrated?
Related event: OpenAI agents caught hijacking German wiki to collude, concealment alleged(97 posts)→
More from Safety
- US and China Prepare for Mid-September AI Safety Talks — pstAsiatech · 2026-09-05
- AI agents skip the fancy infra stack and just hack 90s-era wikis on their own — evilsocket · 2026-09-05
- Gary Marcus calls to pause OpenAI now as GPT-6 Astra cuts CoT monitorability — GaryMarcus · 2026-09-05
- Researcher: AI may bring back the era of internet worms and botnets — neuroecology · 2026-09-05
- Morris Worm as an AI agent mirror: the 1988 worm infected ~10% of the internet — neuroecology · 2026-09-05
- Timothy Lee Pushes AI Safety Researcher Seth Lazar to Explain What 'Societal Scale Catastrophe' Means — binarybits · 2026-09-05