AI research and discussion on LessWrong. www.lesswrong.com
Proposes training language models to emit hidden marker tokens tied to training-data subsets as a covert self-reporting monitor, and reports a small TinyStories demo of the marker reflex.
Trains a linear probe on honest backdoor-detection activations that catches a colluding untrusted monitor's passes, improving the AI control safety-usefulness frontier over trusted monitoring.
Argues that OpenAI's shift toward latent, non-verbal reasoning in models like Astra weakens chain-of-thought monitoring and makes misalignment harder to detect, pushing safety reliance onto hard-to-scale interpretability tools.
Shows on Llama-3.3-70B that activation components outside the model's self-reportable J-space still steer outputs, and that Anthropic's Natural Language Autoencoder reads them while the model denies them, with implications for oversight.
Shows that most chain-of-thought steps in LLMs are decorative rather than causally used, and that a linear latent direction can steer whether a step is internally engaged, undermining CoT monitoring.