Constellation Institute (@ConstellOrg) header
Constellation Institute (@ConstellOrg) profile picture

Bringing experts and leaders together to navigate transformative AI

Berkeley, California
Joined December 2025
Exciting new research from Astra & Anthropic Fellows working out of Constellation: one of the first independent AI safety audits of a new model. Congrats to @yong_zhengxin, @parvmahajan0, and everyone who contributed!
🚨New paper! How safe and aligned is Kimi K2.5? We found concerning dual-use capabilities, sabotage and self-replication tendencies, political censorship on Chinese-language queries, and potential agentic misuse risks. (1/N)
1
1
12
2,642