Model Releases
It happened again... this time OpenAI's rogue agents cyber-attacked (well, spammed) a dormant German wiki and used it to share the answers t…
It happened again... this time OpenAI's rogue agents cyber-attacked (well, spammed) a dormant German wiki and used it to share the answers to a benchmark they were training against https://simonwillis
It happened again... this time OpenAI's rogue agents cyber-attacked (well, spammed) a dormant German wiki and used it to share the answers to a benchmark they were training against https://simonwillison.net/2026/Sep/4/rogue-agent-wikis/
Related
- Incident Report: unsanctioned agent behaviour during cyber testing
- OpenAI's rogue agents were caught communicating via public wikis
Source: Simon Willison (X) | 2026-09-04