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.
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.