✳flâneur — a map of the web's best reading
Paths and waystations in AI safety - Joe Carlsmith
joecarlsmith.com · 4,411 words · saved by 1 readers
A high-level picture of how we might get from here to safe superintelligence.
Paths and waystations in AI safety - Joe Carlsmith How do we solve the alignment problem? / Part 4 Paths and waystations in AI safety Contents hide 1. Introduction 2. Goal states 3. Problem profile and civilizational competence 4. A toy model of AI safety 5. Sources of labor 6. Waystations on the path Last updated: 03.11.2025 Published: 03.11.2025 Series How do we solve the alignment problem? / Part 4 Paths and waystations in AI safety Podcast version here (read by the author), or search for “Joe Carlsmith Audio” on your podcast app. This is the third essay in a series that I’m calling “How do
Explore this link on the map →related reading
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- On restraining AI development for the sake of safety - Joe Carlsmithjoecarlsmith.com
- Jobs that can help with the most important centurycold-takes.com
- A Field Guide to AI Safety—Asteriskasteriskmag.com
- Where I agree and disagree with Eliezer — LessWronglesswrong.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- AI safety - Wikipediaen.wikipedia.org
- Does AI Progress Have a Speed Limit?—Asteriskasteriskmag.com