Dream's threat team recovered an attacker-operated autonomous system's working directory after twelve attack waves over four days. The campaign cracked 85 employee accounts, stole personnel and network data, and expanded toward government suppliers, a nuclear-safety agency, and energy companies. The underlying model and attacker remain unidentified.
Short answers to common questions about the page, its evidence, and the limits of what DoomBench claims.
An item needs a verifiable publication date, an accessible source, a direct connection to the scenarios DoomBench tracks, and enough substance to support a reasoned assessment.
Toward items add pressure in the direction of severe AI outcomes. Away items record evidence of improved control, resilience, governance, or other developments that reduce that pressure.
Yes. Better sources, corrections, or changed context can produce a new revision. DoomBench retains the audit trail and recomputes the chronology without hiding the prior judgment.
No evidence catalogue can guarantee total coverage. DoomBench searches systematically, states its scope, preserves failed-run status, and welcomes credible missing sources rather than presenting partial discovery as completeness.