Comment by BeetleB
7 days ago
The article says it clearly:
> The models themselves may contain malware or other security vulnerabilities.
7 days ago
The article says it clearly:
> The models themselves may contain malware or other security vulnerabilities.
The weights contain malware? What security vulnerability do they contain? Is the claim that they will write insecure code? This seems easy enough to test - run a sufficiently large sample through another LLM
That's true in the sense that it's true for every single model.
Yeah, but it’s different if they’re our backdoors!
Ideally, you have no backdoors.
The next best thing is having backdoors that are there from someone you can find and do something about if things go wrong.
And the article must clearly be the whole truth and nothing but the truth.