Quanta: Injecting 'thoughts' into LLMs to test whether AI can introspect
burny_tech · x · 2026-11-10
Quanta Magazine profiles Anthropic researcher Jack Lindsey's 2025 experiment: injecting 'thoughts' directly into LLM neural networks — a form of digital neurosurgery — to test whether models can introspect on their own thought processes. Introspection has long been debated in philosophy and psychology, with some linking it to consciousness and others calling it an elaborate illusion. The article reviews what a year of follow-up research has revealed since the paper caused a stir online.
More from Research
- PSI claims proof of Aaronson-Ambainis conjecture using a research system built on Claude — burny_tech · 2026-11-10
- PNAS Nexus paper demonstrates experience-based training in a living tissue model — burny_tech · 2026-11-10
- NVIDIA paper: masking ~10 'intrusion heads' recovers 57% of distractor accuracy loss — rohanpaul_ai · 2026-11-10
- The Five Differential Operators of Physics, All Built From One Symbol: Nabla — burny_tech · 2026-11-10
- Control Limit Hypothesis: High Dopamine in Schizophrenia Is Compensation, Not Cause — burny_tech · 2026-11-10
- Interp Researcher's 2026 Advice: Be Ambitious, Pragmatic, and Go Meta — burny_tech · 2026-11-10