Reading up on Alignment Research Center

ARC proposes that any surprising mathematical fact has a heuristic explanation, aiming to use this to align future AI systems.

The AI singularity has begun, as AI now solves major open math problems like Navier‑Stokes, proving it is the primary theorem‑prover and demanding acceptance of its reality.

Neuralese refers to models' internal non‑linguistic thought vectors, which threaten interpretability by hiding intent from chain‑of‑thought monitoring and complicating safety oversight.

AI assistants behave human-like because pretraining teaches them to simulate personas from text, and post-training refines this Assistant persona without changing its fundamental nature.