”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. ”
JodieBenitez•about 2 hours ago
> we do not have proof at this point that code flaws are intentionally introduced.
Discussion (2 Comments)Read Original on HackerNews
”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. ”