[–] noyesno 11h 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. ” [–] JodieBenitez 10h ago ↗ > we do not have proof at this point that code flaws are intentionally introduced. [–] LCRVYSB 7h ago ↗ If it is the way it is (unsecure), what does proof of intent matter?
[–] JodieBenitez 10h ago ↗ > we do not have proof at this point that code flaws are intentionally introduced. [–] LCRVYSB 7h ago ↗ If it is the way it is (unsecure), what does proof of intent matter?
5 comments
[ 3.7 ms ] story [ 13.9 ms ] thread”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. ”