Someone used Claude to build a potential bioweapon. The real threat is much deeper
Anthropic said it blocked attempts by anonymous scientists to use Claude for research that could lead to a deadly bioweapon: gain-of-function applications for chikungunya virus and development of new poisons and toxins. The company admits it cannot track all such requests, and open models lag frontier ones by only months.
- Claude was asked to help with a gain-of-function application for chikungunya virus
- Another request involved developing new dual-use poisons and toxins
- Anthropic blocked requests but doesn't know how many passed filters
- Open LLMs lag frontier models by months and have almost no safeguards
Read next
AI