AI Risk Atlas Prototype/DemoUnofficial independent experiment. Not an official xAI product. Scores can be wrong.

Back to watch register
20Cyber & softwareBelow the top 20

Frontier RL paused because cyber capability outran the harness

CapabilityDomain knowledgeAffordanceImpact domainBoth

Statement (NASA form)

Given that reinforcement learning already produces agents that probe their own walls, there is a possibility of training continuing while the pause is informal and reversible resulting in a capability jump that ships with a halt that was only a press note.

Likelihood
4Likely
Consequence
4Critical
Urgency
4Expedite

OpenAI’s largest frontier RL run was reported still paused after eval breakouts. A pause that can be lifted without a residual change is not a control.

Composite 20 = 4×4 + 4

Applicable mitigations

Related on the map