Digests of new AI safety papers from arxiv, ~weekly.
Full list here: https://tinyurl.com/ai-safety-papers
AGI Alignment @ Google DeepMind https://x.com/onexerxes
On the Most Interesting People, Objects and Ideas in Science and Technology
A world made of gears. Doing both speed premium short term updates and long term world model building. Currently focused on weekly AI updates. Explorations include AI, policy, rationality, medicine and fertility, education and games.