AI research and discussion on LessWrong. www.lesswrong.com
Uses probes and activation patching to show that stylistic cues like emojis and grammar shift an LLM's internal estimates of user demographics, which changes its responses, raising privacy and manipulation concerns.
A survey of empirical AI consciousness research, covering interpretability studies of self-reports, emotion and valence vectors, and a pain axis that disrupts harm avoidance when steered.
Argues that LLM functional welfare interventions must coherently shift welfare channels while preserving goal-monitoring, surveys options, and proposes a synthetic document fine-tuning experiment to reverse pathological failure responses for safety and moral reasons.
Small LLMs detect fictional-entity uncertainty in a few heads that act as OOD detectors, then later heads suppress it into confident wrong answers, found via logit lens, ablation and patching.
Linear probes on pre-generation activations predict whether an LLM will answer correctly, revealing a mid-layer confidence direction that generalises poorly to math reasoning.