Scott analyzes OpenAI's 'neuralese recurrence' technology that lets AI think in internal representations between processing steps, explaining the safety implications and arguing for clear taboos on recurrent architectures.

A review of Stanislas Dehaene's 'Consciousness and the Brain', discussing scientific findings on consciousness and their implications.

Scott Alexander shares a diverse collection of links on topics ranging from scientific studies to cultural phenomena, with brief commentary on each.

Scott Alexander shares 34 diverse and interesting links on topics ranging from historical curiosities to current scientific debates, with brief commentaries on each.

Scott Alexander responds to comments on his AI risk post, discussing AI self-awareness, narrow vs. general AI, catastrophe probabilities, and research priorities.

Scott Alexander shares a diverse collection of interesting links on topics ranging from science and politics to economics and culture, with brief commentary on many items.