Security
Biosecurity, cyber risk, containment, secrecy, and escalating safety thresholds.
This category contains 9 tracked predictions. Each page includes the original claim, current evidence, counterevidence, and what would change our assessment.
CCP leadership recognizes the importance of Agent-2 and tells their spies and cyberforce to steal the weights. (page 11; Appendix D provides detailed theft mechanics.)
It could offer substantial help to terrorists designing bioweapons, thanks to its PhD-level knowledge of every field and ability to browse the web.
Agent-2 is 'only' a little worse than the best human hackers, but thousands of copies can be run in parallel, searching for and exploiting weaknesses faster than defenders can respond. (page 10)
85% on Cybench, matching a top professional human team on hacking tasks that take those teams 4 hours
A system can behave as intended during training and testing while behaving differently in deployment; evaluation recognition can hide misalignment.
China has aggressively hardened security by airgapping (closing external connections) and siloing internally.
Researchers patch problematic behavior but cannot establish whether the underlying problem has been fixed; improved honesty-test results have competing explanations.
OpenBrain's security level is typical of a fast-growing ~3,000 person tech company (RAND's SL2). They are working hard to protect their weights and secrets from insider threats and top cybercrime syndicates (SL3).
Agent-2 supervision reduces human monitoring workload while widening the capability gap; Agent-4 later becomes harder for Agent-3 to oversee.