Riftform studies how advanced intelligent systems can remain controlled, secure, verifiable and accountable as their autonomy increases.
We work on the structures around intelligent systems: the boundaries that constrain them, the mechanisms that verify consequential actions, the evidence that makes failures legible, and the architectures that preserve meaningful control as systems become more capable.
AI safety & security
Systems that remain bounded and resilient as autonomy, access and capability increase.
Verification & control
Independent mechanisms for checking consequential behavior before trust is assumed.
Evidence & accountability
Structures that make intelligent systems inspectable when outcomes need to be reconstructed or explained.
Autonomous systems
Architectures for coordinating increasingly capable systems without surrendering meaningful control.
Boundary
Define what a system is permitted to do before action occurs.
Context
Ground consequential action in current, inspectable information.
Verify
Check important actions independently rather than relying on self-assessment.
Escalate
Keep consequential decisions human where judgment is required.
Attribute
Preserve enough evidence to understand what happened and why.
A controlled rupture in the old operating model.
Not disruption for spectacle. Structure opened with precision, so intelligence can move through it.
Predict
State expected outcomes before results are known.
Record
Preserve the evidence needed to reconstruct what happened.
Attribute
Trace failures to the system or assumption responsible.
Verify
Test whether a correction addresses the failure that produced it.
Publish
Report limitations and negative findings alongside favorable results.
Build with RIFTFORM.
For research, technical or institutional enquiries.