Tracking AI existential risk. Source-backed context. Original reporting always linked.
MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY
Research

Proposal for tracking the effects of architecture on monitorability

Zac Boring September 10, 2026 1 min read
Read original source →

Key takeaway

Architectures that incorporate opaque recurrence or allow for agents to communicate with each other using latents could rapidly make it much harder to monitor chains of thought or communication (we’ll refer to this property as “monitorability” going…

Why it's on PDOOM

PDOOM selected this story as relevant to alignment & control.

From Alignment Forum

Architectures that incorporate opaque recurrence or allow for agents to communicate with each other using latents could rapidly make it much harder to monitor chains of thought or communication (we’ll refer to this property as “monitorability” going forward).[1] As companies begin to explore such architectures, we believe it is important to transparently share evidence about how monitorability varies with architecture and training method. To inform the scientific debate on how to make tradeoffs

By ryan_greenblatt

Read the full article at Alignment Forum →