It may have been backdoored during training, potentially causing it to randomly start wreaking havoc at runtime, possibly in a clandestine manner (e.g. sneaking in bugs into generated code).
This isn't a security issue related to self-hosting, it's a security issue related to use and it is shared entirely by closed weights models. Anthropic could easily be sneaking bugs into your generated code, too.
It may have been backdoored during training, potentially causing it to randomly start wreaking havoc at runtime, possibly in a clandestine manner (e.g. sneaking in bugs into generated code).
This isn't a security issue related to self-hosting, it's a security issue related to use and it is shared entirely by closed weights models. Anthropic could easily be sneaking bugs into your generated code, too.
Correct, that was not my point either.
2 replies →
e.g. be trained to favour including compromised dependences into your projects.