Open-source language models could simplify bioterrorism, study finds

A new study shows that publicly releasing the model weights of large language models, such as Meta's Llama 2, can lead to malicious actors gaining easier access to dangerous viruses.

The article Open-source language models could simplify bioterrorism, study finds appeared first on THE DECODER.

actors ai and safety ai research article artificial intelligence decoder language language models large language large language models llama llama 2 meta open source shows study the decoder viruses