Anthropic:

A study finds that as few as 250 malicious documents can produce a “backdoor” vulnerability in an LLM, regardless of model size or training data volume  —  Read the paper … Large language models like Claude are pretrained on enormous amounts of public text from across the internet …

Anthropic:

A study finds that as few as 250 malicious documents can produce a “backdoor” vulnerability in an LLM, regardless of model size or training data volume  —  Read the paper … Large language models like Claude are pretrained on enormous amounts of public text from across the internet …

Source: TechMeme
Source Link: http://www.techmeme.com/251009/p45#a251009p45