Back to News
Advertisement
Advertisement

Discussion (2 Comments)Read Original on HackerNews

noyesnoabout 3 hours ago
TLDR;

”1. Chinese LLMs produce more vulnerable code when prompted with a U.S. government persona than without—and the vulnerabilities are highly obfuscated.

2. Chinese LLMs inject PRC-aligned political bias into both the answers and code they generate. ”

JodieBenitezabout 2 hours ago
> we do not have proof at this point that code flaws are intentionally introduced.