Specifically, the paper estimates that Llama 3.1 70B has memorized 42 percent of the first Harry Potter book well enough to reproduce 50-token excerpts at least half the time. (I’ll unpack how this ...

Each row represents a different model. The three bottom rows are Llama models from Meta. And as you can see, Llama 3.1 70B—a ...

LLM developers are increasingly turning to synthetic data to speed up development and reduce costs. Researchers behind ...

Meta's Llama 3.1 AI reportedly memorizes large parts of copyrighted books like Harry Potter, raising concerns about legal ...

Scientists at Massachusetts Institute of Technology have devised a way for large language models to keep learning on the ...