
Wrote an essay series on solving the AI alignment problem, discussing the importance of building AIs that do human-like philosophy.
How media typically covers Joe Carlsmith
Referenced in coverage
Building AI systems capable of human-like philosophy is critical for safe out-of-distribution generalization, requiring both capability in philosophical reasoning and disposition to engage in that reasoning when needed.
“Wrote an essay series on solving the AI alignment problem, discussing the importance of building AIs that do human-like philosophy.”