AI research and discussion on LessWrong. www.lesswrong.com
Argues for interpretable, narrow models in high-stakes settings as a route to regulation, and reports that tensor-network transformers remain competitive while mechanistic interpretability is still unsolved.
A career guide for outsiders transitioning into technical AI safety, covering interpretability, alignment, control, required skills, and learning resources. It mainly offers practical advice rather than new research findings.
Assesses whether training data attribution can become a practical frontier-LLM tool, covering its feasibility, obstacles from labs' data secrecy, possible policies, and its modest expected value for reducing large-scale AI risk.