Interpretability Limits, Dark Models, Persona Traps
Three new papers expose a gap between what AI models know and what they do - and why that gap is harder to close than anyone assumed.
Interpretability
Reasoning Models Can't Hide Their Thinking - OpenAI Study
OpenAI's CoT-Control benchmark shows frontier reasoning models score 0.1-15.4% at steering their own chain of thought - a result the company frames as good news for AI oversight.
AI Research Roundup: Agent Behavioral Contracts, Autonomous Memory, and Certified Circuits
Three new papers tackle agent reliability through formal contracts, active knowledge acquisition for memory systems, and provably stable mechanistic interpretability.
Guide Labs Open-Sources Steerling-8B, an LLM That Shows Its Work
YC-backed startup Guide Labs releases Steerling-8B under Apache 2.0 - an 8.4B parameter model with a built-in concept module that traces every output token back to its training data.
