News for hackers. Stuff that matters.
Re:Microsoft Phi-2 model changes licence to MIT by acdha on Saturday January 06, 2024 @10:29AM (#38892192)
That’s somewhat true – it’s not easy but not hard enough, as we saw with the Aum Shinrikyo attacks – but an LLM won’t magically have access to non-public instructions and, not having an understanding of the underlying principles, won’t be able to synthesize a safe process from public information.
Re:Microsoft Phi-2 model changes licence to MIT by pixl97 on Saturday January 06, 2024 @12:20PM (#38893218)
Eh that is up for debate. If I dump a library of chemistry books and industry books on chemistry and volatile chemicals its distinctly possible the model could generate this data.
Re:Microsoft Phi-2 model changes licence to MIT by acdha on Saturday January 06, 2024 @12:30PM (#38893304)
Not without some kind of understanding of the underlying principles. If you were testing something verifiable in code you might be able to test candidates at scale, but this involves a number of real-world processes which would be hard to tackle that way.