What holds AI safety together? Co-authorship networks from 200 papers — LessWrong
lesswrong.com · 1,904 words · saved by 3 readers
We (social science PhD students) computed co-authorship networks based on a corpus of 200 AI safety papers covering 2015-2025, and we’d like your hel…
x What holds AI safety together? Co-authorship networks from 200 papers — LessWrong AI Governance AI Frontpage 35 What holds AI safety together? Co-authorship networks from 200 papers by Anna Thieser 25th Apr 2026 1 min read 10 35 We (social science PhD students) computed co-authorship networks based on a corpus of 200 AI safety papers covering 2015-2025, and we’d like your help checking if the underlying dataset is right. Co-authorship networks make visible the relative prominence of entities involved in AI safety research, and trace relationships between them. Although frontier labs produce
saved by
related reading
- AI in 2025: gestalt — LessWronglesswrong.com
- AI safety undervalues founders — LessWronglesswrong.com
- Ten people on the inside — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.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
- In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?saif.org
- [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
- Field map – AISafety.comaisafety.com
- Automated Alignment is Harder Than You Think — LessWronglesswrong.com
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org