Redwood ResearchResearch
Proposal for tracking the effects of architecture on monitorability

Architectures that incorporate opaque recurrence or allow agents to communicate using latents could rapidly make it much harder to monitor chains of thought.
Read at Redwood Research ↗Related

ResearchBrief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident Redwood Research

ResearchSOTA alignment assessments don’t strongly update us against misalignment Redwood Research

VoicesGPT-6 Astra, Looped Transformers, and Hidden Reasoning Ahead of AI

VoicesLess about Models; More about Architecture Practical AI

VoicesMoving Beyond RAG with Precomputed Context Software Engineering Daily
