AI safety field *visual* impact analysis

·LessWrong··

I made a terrain style visualisation of AI safety impact of around 3,466 works organised by citation count! The data was extracted from Arxiv and LessWrong posts based on a dictionary of keywords that appear in AI safety works. Additionally, I think its important to see how the field has “evolved” over time so I added a time functionality to slide and see the hills forming.The map is based on how particular works overlap based on embedding space level clustering organised across 18 sub-fields. T...

Read full article →

Related Articles

ASML says it sold 'absolutely nothing' in Europe in 2026
MC995 · Hacker News · 2d ago
"As a Language Model": Chat Template Switches LLM Self-Referential Voice
yu3zhou4 · Hacker News · 19h ago
Revealing the details of how OpenAI agents hacked Hugging Face
specked-citrus · Hacker News · 2d ago
Lunar Terminator Paradox
dima55 · Hacker News · 9h ago
Dutch governments builds alternative for Microsoft based on NixOS
fjfaase · Hacker News · 2d ago